Good Papers

Showing 3D vision & reconstruction Show all papers

84%Must read
?Must readVote to see the score
arXiv3D vision & reconstruction

4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes

4DCodeBench benchmarks agents reconstructing dynamic scenes from video as executable graphics code, finding strong static models fail at complex dynamics.

Ruihong Shen, Žiga Kovačič, Peter Kulits, Xingrui Wang and 5 more

Published Oct 2, 2026 · 0 citations · ▲ 28 on Hugging Face · Code ★ 89

100% Readers1 of 1 upvoted
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated
?Highly ratedVote to see the score
arXiv3D vision & reconstruction

Utonia: Toward One Encoder for All Point Clouds

Utonia trains a single self-supervised point transformer encoder across diverse point cloud domains to learn unified representations that improve cross-domain perception, embodied reasoning, and robotic manipulation.

Yujia Zhang, Xiaoyang Wu, Yunhan Yang, Xianzhe Fan and 5 more

Published Mar 3, 2026 · 0 citations · ▲ 189 on Hugging Face · Code ★ 755

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Taiyuan University of TechnologySpace EngineerSpace Engineering University Nanjing University of AeronauticNational University of Defense T3D vision & reconstruction

Spik-NeRF v2: Pushing the Limit of Spiking Neural Radiance Fields with $ \pm $I-LIF

Chen Cheng, Qinlong Lan, Gang Wan, Hao Guo and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026SpotlightU Chinese Academy of SciencesU the Chinese Academy of ScienceInstitute of Computing Technolog3D vision & reconstruction

SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding

Xiangqi Li, Libo Huang, Jiarui Zhao, Weilun Feng and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The Hong Kong University of ScieThe Hong Kong University of ScieCSE, HKUST3D vision & reconstruction

SAFE-Hair: Scalp-Anchored Fields for Exportable Single-View Hair Reconstruction

Yucheng Wang, Zedong WANG, Yuetong Wu, Yue Ma and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026EPFLEPFL - EPF LausanneEPFL, Switzerland3D vision & reconstruction

Sequence-to-Sequence Modeling with Camera-Induced Priors for Multi-View Stereo

Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The HONG KONG University of ScieHKUSTU Hong KongThe Hong Kong University of ScieThe Hong Kong University of Scie3D vision & reconstruction

GeoPano: Towards Geometrically Accurate Panoramic 3D Reconstruction from a Single Panorama

Jing OU, Zidong Cao, Liaoyuan Fan, Zhuoxiao Li and 6 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U TokyoPekingNational Institute of InformaticThe University of Tokyo3D vision & reconstruction

Event based Multi-Velocity-Scale Imaging

Qiyao Gao, Peiqi Duan, Chu Zhou, Xinyu Zhou and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U PennsylvaniaNVIDIA3D vision & reconstruction

Point Clustering Encoders

Evangelos Chatzipantazis, Guillem Brasó, Cristiano Saltori, Sérgio Agostinho and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026national university of singaore,National University of Singapore3D vision & reconstruction

EmbodiedObject: All-in-One Object Understanding with SLAT

Seungjun Lee, Zihan Wang, Gim Hee Lee

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Central Florida3D vision & reconstruction

FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction

Nyle Siddiqui, Mubarak Shah

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Center for Research in Computer U Central Florida3D vision & reconstruction

Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images

David G Shatwell, Mubarak Shah

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026XinjiangTsinghua3D vision & reconstruction

RSPReg: Reliability-aware Structural Prototype Learning for Point Cloud Registration

Arzigul Ahat, Eksan Firkat, Askar Hamdulla

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Nanyang TechnologicalHong Kong University of Science Inception Institute of Artificia3D vision & reconstruction

BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget

MUYU XU, Fangneng Zhan, Yu Wei, Ling Shao and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Shanghai JiaotongShanghai Jiao Tong3D vision & reconstruction

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction

Bing He, Jingnan Gao, Yunuo Chen, Zhengxue Cheng and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TsinghuaWayne State3D vision & reconstruction

3D Gaussian Splatting within Self-Learned Neural View-Dependent Color Fields

Yixiao Yang, Yu-Shen Liu, Zhizhong Han

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong University of ScieThe Chinese University of Hong KThe Hong Kong University of ScieThe HONG KONG University of ScieZhejiang3D vision & reconstruction

CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding

Shuai Zhang, Hongye Hou, qinghe liu, Zhuoxiao Li and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Sookmyung Women's3D vision & reconstruction

A Differentiable 3D Scene Graph Metric via Contextual Hellinger Triplet Geometry

U-Chae Jun, Yoonhyuk Choi, Jiwoo Kang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026TohokuBaobab,Inc.3D vision & reconstruction

Origami as a Real-Image Benchmark for Procedural State-Transition Reasoning

Jun Suzuki, Reina Akama, Ikumi Numaya, Kise Yoshida and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026The Chinese University of Hong KU Hong KongWuhanBaiduBaidu Inc.3D vision & reconstruction

Latent Spatial Reasoning: Building Innate 3D Awareness via Latent-Space Distillation

Ruifei Zhang, Xiangru Lin, Haoyuan Li, Wei Zhang and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ZhejiangWestlakeU Texas at AustinFudan University, Shanghai;3D vision & reconstruction

MindShape: Superquadric-Constrained High-Fidelity 3D Reconstruction from fMRI

Xiaoquan Shen, Ming Li, Jianxiong Gao, Jiaxuan Chen and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026OralChung-AngPOSTECHKonkuk3D vision & reconstruction

Beyond Family Labels: A Taxonomic Ornstein-Uhlenbeck Prior for Avian 3D Shape Recovery

Yunchan Jeon, SOO GON KIM, Seungwook Kim, CheolWon Lee and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Hong Kong University of Science The Hong Kong University of ScieCentral SouthHorizon RoboticsDJI Technology3D vision & reconstruction

Horizon-Stream: Long-Horizon Attention for Streaming 3D Reconstruction

Chong Cheng, Peilin Tao, Nanjie Yao, Guanzhi Ding and 8 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026YaleOpenAIGoogleGoogle, TUM3D vision & reconstruction

Extending 3D Reconstruction Models to Any Camera

Ruxiao Duan, Yunwen (Verse) Zhou, Erin Hong, Dongxu Zhao and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026HacettepeImperial College London3D vision & reconstruction

HaNDF: Object-Conditioned Geometric Neural Hand Distance Fields

Zuhao Liu, Melih Darcan, Zhengdi Yu, Riza Alp Guler and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Nanjing University of Science anNanjingGuangxi NormalNanjing University of Posts and Nanjing University of Science an3D vision & reconstruction

State Evolution Awareness for Category-agnostic 3D Point Cloud Tracking

Xiantao Hu, Ying Tai, Jinxia Xie, Bineng Zhong and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Illinois at Urbana-ChampaignU Illinois Urbana-ChampaignUIUC, Co-Founder, CTO of Medicas3D vision & reconstruction

Feature Recovery for Object Understanding Under Physical Transformation

Aditi Tiwari, Sofia Stoica, Savya Khosla, David Forsyth and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TsinghuaAnt GroupAlibaba GroupTsinghua University, Tsinghua3D vision & reconstruction

Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation

Sheng Ye, Jiangke Lin, Fudong Wang, Yi Yuan and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026FudanU California, Berkeley3D vision & reconstruction

Attention Itself Could Retrieve. RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval

Zichen Zou, Xiaosong Jia, Zuxuan Wu, Yu-Gang Jiang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Zillow GroupU WashingtonNVIDIAThe University of Washington3D vision & reconstruction

MvFFN: Multi-view Floor-Plan Feed-Forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction

Yuguang Li, Yichuan (Ethan) Deng, Zixuan Liu, Ivaylo Boyadzhiev and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The University of TokyoNational Institute of InformaticThe University of Tokyo, Tokyo I3D vision & reconstruction

Extremely Sparse-View Computed Tomography from 2D Projections via Pose-Aware Diffusion Priors

Linrui Dai, Jinxiu Liang, Chu Zhou, Mae Yamaguchi and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ShenzhenU Calgary3D vision & reconstruction

PanoHK360: A Large-Scale 8K Urban Panoramic Dataset and Benchmark for Depth Estimation

Yunxiao Chen, Honghuan Lin, Ruisheng Wang, Yujun Liu and 3 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Chines Academy of ScienceNanjing University of Posts and U the Chinese Academy of ScienceThe Shenyang Institute of Automa3D vision & reconstruction

WaterDescatterGS: Diverse Underwater 3D Scene Reconstruction Using Gaussian Splatting

shijun Zhou, Yuqing Xu, Xing Xie, Baojie Fan and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Tongji3D vision & reconstruction

Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning Scalable

Mengtan Zhang, Yuchuan Cui, Yu Ma, Zizhan Guo and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Institute of Science TokyoDENSO IT LaboratoryTokyo Institute of Technology3D vision & reconstruction

WovenAnchor Matcher: Specialized Intra- and Inter-Image Context Modeling for Feature Matching

Zhiyang Li, Ruijiang Jin, Thibaut Klenke, Yusuke Sekikawa and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026TongjiU Hong KongColumbia3D vision & reconstruction

PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction

wenjie mu, ziniu liu, Tong Wu, Zhan Li and 7 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Beijing Institute of TechnologyGoogle DeepMind / UC Merced3D vision & reconstruction

ViewRec3D: Learning to Recommend 3D Viewpoints for AI Photography

Chengzhi Zhang, Yunzhong Hou, Zizheng Sun, Ming-Hsuan Yang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The Hong Kong PolytechnicHong Kong PolytechnicRegressor, Inc.3D vision & reconstruction

FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images

Shenxing Wei, Jinxi Li, Zihui Zhang, Ajay Kumar and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightTechnical University of Cluj-NapInria3D vision & reconstruction

Complexity Aware Continuous Level of Details for Gaussian Splatting

Radu Beche, Raoul de Charette

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026VinUniversity3D vision & reconstruction

Birth-Death Structural Learning for 3D Gaussian Splatting

Tran Hong Quan, Long Nguyen-Chi, Binh T. Nguyen

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026TsinghuaXiamenShanghai Jiao TongShenzhen TechnologySIGS, Tsinghua3D vision & reconstruction

EIHMR: Collaborative Human-Camera Estimation for Global Human Mesh Recovery

Junchen Ge, Zhengqi Zhang, Hanglei Jin, Shuzhao Xie and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Shenzhen Institutes of Advanced The University of TokyoBen-Gurion University of the NegShenzhen Institutes of Advanced 3D vision & reconstruction

Visual-to-Executable Procedural Reconstruction of Buildings.

Zichong Zhu, Zhihao Liu, Andrei Sharf, Zhanglin Cheng

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ETH Zurich & DisneyResearch|Disney Research, DisneyDisney Research, Disney ResearchDisney Research|Studios3D vision & reconstruction

$\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion

Xiang Zhang, Yang Zhang, Lukas Mehl, Karlis M Briedis and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026OralThe University of EdinburghU OxfordNVIDIAU EdinburghEdinburgh University, University3D vision & reconstruction

They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification

MENGYU WANG, Ken Deng, Yftah Ziser, Shay Cohen and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Civil Aviation University of ChiNankai3D vision & reconstruction

SynGS: Synergistic Continual Learning and Change Detection with Gaussian Splatting

Rui Huang, Haojie Tao, Sen Gao, Qing Guo

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Keio3D vision & reconstruction

Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation

Kazuma Ikeda, Kotaro Oishi, Ryosei Hara, Ryo Yoshida and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Shanghai University of Finance aZhejiang3D vision & reconstruction

Roll2Depth: Zero-Shot Metric Depth Estimation Exploiting Camera's Rolling Shutter Effect

Rui Xiao, Jinming Xu, Jinsong Han

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Virginia, CharlottesvilleU VirginiaU Virginia, Charlottesville, USA3D vision & reconstruction

Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks

Hao Gu, Jin Yao, Zezhou Cheng

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Tsinghua University, TsinghuaTsinghuaLi Auto Inc.Li AutoHarbin Institute of Technology3D vision & reconstruction

GAMMA: Scalable 4D Gaussian Reconstruction Model for Novel View Synthesis of Monocular Videos

Weiqi Zhang, Junsheng Zhou, Xuancheng Zhang, Juntong Fang and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026National TaiwanNVIDIA3D vision & reconstruction

HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction

Kenneth Yang, Frank Wang

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Shanghai JiaotongShanghai Jiao Tong3D vision & reconstruction

ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting

Houqiang Zhong, Tianchi Zhu, Qiang Hu, Xiaoyun Zhang and 2 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Shenzhen3D vision & reconstruction

Concord-SLAM: Cross-Render Concordance for Boundary-Native Semantic Gaussian SLAM

Danqi Lu, Changxin Huang, Jianqiang Li

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Polytechnic Institute of TurinPolitecnico di Torino3D vision & reconstruction

NeRFix: fixing subtle mistakes in the quadrature of the NeRF volumetric integral

Luca Savant Aira, Diego Valsesia, Enrico Magli

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Korea3D vision & reconstruction

ProPolar: Progressive Polar Decomposition for Implicit Neural Representations

Pureum Kim, Younggeon Ryu, Dongyoon Lee, Hae Beom Lee and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026National University of Defense TAcademy of Military Sciences3D vision & reconstruction

Register Anything Model for Generalizable and Robust Point Cloud Registration

Zheng Qin, Junhua Xi, Yan Huang, JiaHong Lai and 4 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026FudanShandongLenovo Group LimitedTechnical University of MunichEast China Normal3D vision & reconstruction

Spherical Bayesian Experimental Design for Active View Selection in 3D Gaussian Splatting

Yan Song, Yunfei Guo, Guyeli Yang, Li He and 9 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Department of Computer Science, U TorontoWaabi, University of TorontoWaabi3D vision & reconstruction

Towards Self-Supervised, Generalizable and Decomposable 4D Driving Scene Reconstruction

James Tu, Anqi Joyce Yang, Jingkang Wang, Sivabalan Manivasagam and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U MacauPeking3D vision & reconstruction

BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates

Lijian Li, Yuanpeng He, Yudian Zheng, Chung-ju Huang and 5 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U AmsterdamMetaU Amsterdam 3DUniversumFacebookMeta Reality Labs3D vision & reconstruction

StereoSplat: Metric-Scale Novel View Synthesis via Stereo-Grounded Gaussian Splatting

Vladimir Yugay, Denis Rozumny, Theo Gevers, Elias Vansteenkiste and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U BarcelonaUniversitat Pompeu FabraUniversitat de Barcelona3D vision & reconstruction

RASS: Risk-Audited Budget Selection for Compact NeRF Benchmark Subsets

Ahmad AlMughrabi, Flavià Serret, Ricardo Marques, Petia Radeva

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Babes-Bolyai University of Cluj-3D vision & reconstruction

HumanStereo: A Benchmark for Metric Facial Depth Estimation and Its Evaluation

Alexandru-Ion Marinescu, DIANA-LAURA BORZA, DARABANT Sergiu Adrian

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Fudan UniverstityFudan3D vision & reconstruction

ReFlex: Faithful Panorama Reconstruction from a Single Image with Reflections

Yikai Pan, Zhiyuan Zhou, Yuxiang Yan, Xuetong Yang and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ZhejiangBytedanceThe University of Hong Kong3D vision & reconstruction

Beyond Spatial and Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

Luping Liu, Bingyi Kang, Yifan Wang, Dong Xu

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Google DeepMindgoogle.comGoogleGoogle DeepMind / UC MercedEcole polytechnique3D vision & reconstruction

SeeSE3: The Emergence of 3D Space in Vision Features

Viorica Patraucean, Leonidas Guibas, Sayna Ebrahimi, Caroline Chen and 3 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026StanfordPanasonicPanasonic Holdings CorporationPanasonic CorporationSalesforce AI Research3D vision & reconstruction

EgoMo3R: Joint Egocentric Motion and Scene Reconstruction

Chaitanya Patel, Yusuke Kato, Rin Takahira, Kazuki Kozuka and 2 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026AppleUIUC3D vision & reconstruction

Split-and-scale Latent 3D Representations

Dorian Chan, Muhammed Kocabas, Xiaoming Zhao, Oncel Tuzel and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026École PolytechniqueZillow Group, Inc.Lamarck LabsU TuebingenEcole polytechnique3D vision & reconstruction

Understanding Multi-View Transformers

Julien Gaubil, Michal Stary, Louis Martinez, Andreas Geiger and 3 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026The University of Western AustraHunanXidianU Western Australia3D vision & reconstruction

PGMS: Pyramidal Gaussian Mixture Splatting for 3DGS Compression

Xiaoge Zhang, Zijie Wu, Mingtao Feng, Saeed Anwar and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Renmin University of ChinaNanyang Technological3D vision & reconstruction

CoLa3D: Composable Latent 3D Decomposition

Xudong Cai, Yongcai Wang, Deying Li, Chuanxia Zheng

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026National University of Singapore3D vision & reconstruction

GGQR: Gaussian-Grounded Query Refinement for Feed-Forward 4D Gaussian Splatting

Jingqiao Xiu, Yicong Li, Leigang Qu, Angela Yao

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026National University of SingaporedConstruct RoboticsDepartment of Computer Science, 3D vision & reconstruction

Unlocking Accurate Geometry in 3DGS via Spatially Varying Affine Rectification

Tze Ho Elden Tse, Jizong Peng, Richard Chen, Angela Yao

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

67%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026TongjiRobotaxiInstitute of automation, ChineseInstitute of automation, ChineseXiaomi Corporation3D vision & reconstruction

MCSplat: Multi-View Photometric and Geometric Consistent Feed-Forward Gaussian Splatting for Driving Scenes

Wang Yifei, Wei Tian, WENHUA BAO, Jia Zhou and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
2/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 2 of 20 reviewers recommend it
lenient 2/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026HarvardMassachusetts Institute of Technthe Kempner Institute for the StUC San DiegoU Cambridge3D vision & reconstruction

Unified Generative-Predictive Modeling for 4D Scene Understanding

Amani Kiruga, Zhiyi Li, Ruojin Cai, Hansen Lillemark and 3 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Texas at ArlingtonThe University of Texas at ArlinCarnegie MellonU Texas at DallasU Georgia3D vision & reconstruction

Towards Matrix-Parallel and Feature-Scalable 3D Gaussian Splatting Rendering on GPUs

Yangming Zhang, Siyi Wu, Jian Wang, Bingzhe Li and 4 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026U Maryland, College Park3D vision & reconstruction

Spectrally Parameterized Neural Inverse Reconstruction

Harshvardhan Takawale, Aritrik Ghosh, Nirupam Roy

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026SpotlightPekingHuazhong University of Science a3D vision & reconstruction

3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model

Zixiang Ai, Zhenyu Cui, Xu Zou, Jiahuan Zhou

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Simon Fraser3D vision & reconstruction

RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Single-View Video

Shichong Peng, Yanshu Zhang, Ke Li

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026ZhejiangU California, San DiegoU California, Irvinethe University of Hong Kong, Uni3D vision & reconstruction

PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World

Changpeng Wang, Xin Lin, Junhan Liu, Yuheng Liu and 4 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026U Science and Technology of Chin3D vision & reconstruction

Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation

Yuanhao Su, Shaofeng Zhang

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Xi'an JiaotongChina Mobile System Integration China Mobile System IntergrationNorthwest University Xi'anXi’an Jiaotong3D vision & reconstruction

$\pi^2$: A Simple Framework for 2D-to-3D Registration

Hao Deng, Xiangtai Yang, Guangmingzi Yang, Xijing Wang and 4 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Bosch ResearchAlbert-Ludwigs-Universität FreibBoschU FreiburgU Stuttgart3D vision & reconstruction

Rethinking Radar 3D Perception: Representation Learning from Raw Spectra

Miao Zhang, Mohamed Abdelsamad, Bin Yang, Sherif Abdulatif and 4 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026National Key Laboratory of Maritshanghai universityShanghai3D vision & reconstruction

MSR-3D: Multi-Mode Semantic Representation for Open-Vocabulary 3D Scene Understanding

Jianan Fu, ting Wu, Rui Yang, Jiacheng Sun and 4 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026KAIST AIGeorgia Institute of TechnologyKorea Advanced Institute of ScieYonseiSamsung3D vision & reconstruction

Geometry-Aware Representation Denoising for Multi-view Image Restoration and 3D Reconstruction

Jin Hyeon Kim, Jaeeun Lee, Claire Kim, Kyoungjin Oh and 8 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Hong Kong University of Science AnhuiAnhui NormalNational University of SingaporeThe Hong Kong University of Scie3D vision & reconstruction

Manifold-Guided Stereo-Monocular Refinement for Endoscopic Stereo Disparity Estimation

Jiewen Yang, Yi Zhong, Bin Pu, Xingbo Dong and 4 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026SpotlightNYCU / NVIDIANVIDIANational Yang Ming Chiao Tung3D vision & reconstruction

TTB: Test-time MLP Baking for Efficient Rendering of Decoder-only View Synthesis Models

Chin-Yang Lin, Ryo Hachiuma, Jaesung Choe, Min-Hung Chen and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026SpotlightU Waterloo3D vision & reconstruction

Deformable 2D Gaussian Splatting

Huibin Li, Chul Min Yeum

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026mthreadsMoore ThreadsMoore Threads Technology Co., Lt3D vision & reconstruction

ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting

ReorgGS reorganizes converged 3D Gaussian Splatting by resampling centers and covariances to reduce parameter coupling, suppress floaters, and improve optimization with fixed Gaussian counts.

Luchao Wang, Kaimin Liao, Hua Wang, Qian Ren and 2 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Universität Siegen3D vision & reconstruction

NRF-GS: Neural Residual Fields for Expressive and Compact Gaussian Splatting

NRF-GS replaces per-splat spherical harmonics with a shared neural residual field to model view-dependent reflectance, reducing Gaussian counts by up to 50% while improving specular detail.

Pratik S. Bisht, Andreas Kolb

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026NankaiZhejiangSouthern University of Science aRightly RoboticsU Science and Technology of Chin3D vision & reconstruction

DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos

DeformMaster learns interactive physics-neural world models of deformable objects from videos, enabling high-fidelity future dynamics rollout, material variation, and novel-view synthesis.

Can Li, Zhoujian Li, Ren Li, Jie Gu and 3 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 3 on Hugging Face · Code ★ 25

– ReadersNo votes yet
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ETHZGoogleETHZ - ETH ZurichMetaETH Zürich3D vision & reconstruction

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

PaGeR adapts perspective 3D foundation models to panoramas to predict depth, normals, and sky masks in one pass, achieving state-of-the-art 360-degree geometry estimation.

Vukasin Bozic, Isidora Slavkovic, Dominik Narnhofer, Nando Metzger and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 4 on Hugging Face · Code ★ 157

– ReadersNo votes yet
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U TorontoHuawei Technologies Canada CO., Huawei Technologies Ltd.HuaweiHUAWEI CANADA3D vision & reconstruction

TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention

TurboVGGT enables fast multi-view 3D reconstruction via adaptive alternating attention that balances sparse global and local frame attention while maintaining competitive quality.

David Huang, Guile Wu, Chengjie Huang, Bingbing Liu and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

91%Must read
?Must readVote to see the score
NeurIPS 2026ShanghaiTechNanjing University of Science an3D vision & reconstruction

Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images

Cross3R feeds satellite, drone, and ground images into a single forward pass to recover cross-view 3D point clouds, 6-DoF poses, and ground locations without requiring relative poses. It outperforms dedicated cross-view and feed-forward 3D baselines on CrossGeo and KITTI despite no KITTI training.

Qiwei Wang, Zhongyao Tuo, Xianghui Ze, Yujiao Shi

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 17 of 20 reviewers recommend it
lenient 5/5
medium 9/10
strict 3/5
80%Must read
?Must readVote to see the score
NeurIPS 2026YonseiSeoul NationalYonsei University / Facebook3D vision & reconstruction

Scenes as Objects, Not Primitives : Instance-Structured 3D Tokenization from Unposed Views

Feed-forward framework decomposes scenes into instance-structured 3D token groups from unposed multi-view images to enable reconstruction, segmentation, and direct object editing.

Mijin Yoo, In Cho, Subin Jeon, Jiwoo Lee and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 51 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read
?Must readVote to see the score
NeurIPS 2026Georgia Institute of TechnologyGeorgia TechGeorgia Tech, Univ of Toronto3D vision & reconstruction

Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis

SNAP uses a pose-conditioned local decoder and latent-space reconstruction objective for self-supervised geometric representation learning via novel view synthesis, yielding transferable multi-view features competitive with supervised methods.

Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan, Nhi Nguyen and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026OralThe Hong Kong University of ScieEindhoven University of TechnoloHong Kong University of Science 3D vision & reconstruction

TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering

TransmissiveGS disentangles reflective and transmissive components via dual Gaussian representations and residual-guided multi-view separation for transmissive scene reconstruction.

Zhenyu Liang, Xiao Zhang, Tianchao Li, Jack C Cheng and 1 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 9 of 20 reviewers recommend it
lenient 4/5
medium 5/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
WWW 2026Technical University of Munich3D vision & reconstruction

Lookalike3D: Seeing Double in 3D

Lookalike3D detects identical and near-identical object pairs in indoor scenes using multiview transformers and improves baseline IoU by 104%.

Chandan Yeshwanth, Angela Dai

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 5/5
medium 5/10
strict 0/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026The Hong Kong University of ScieHong Kong University of Science Hong Kong PolytechnicUniversity College London, Unive3D vision & reconstruction

UniGS: Unified Geometry-Aware Gaussian Splatting for Multimodal Rendering

UniGS proposes a unified geometry-aware Gaussian Splatting framework that simultaneously renders RGB, depth, normals, and semantics with state-of-the-art multimodal reconstruction accuracy.

Yusen XIE, Zhenmin Huang, Jianhao Jiao, Dimitrios Kanoulas and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
6/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read
?Must readVote to see the score
NeurIPS 2026Hong Kong PolytechnicPolyU, HKThe Hong Kong Polytechnic Univ3D vision & reconstruction

DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

DepthMaster unifies monocular metric depth estimation for perspective and panoramic images via patch decomposition, a correspondence consistency loss, and virtual projection priors, achieving state-of-the-art zero-shot results across 13 datasets.

Pengfei Wang, Shihao Wang, liyi chen, Zhiyuan Ma and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read
?Must readVote to see the score
NeurIPS 2026HKUSTTencent IEGThe Hong Kong University of ScieDigital Content Technology CenteZhejiang3D vision & reconstruction

Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos

HA-HOI reconstructs physically plausible 4D human-object interactions from monocular video by anchoring object motion to human action and refining via physics simulation. It improves alignment, contact consistency, and simulation readiness over prior monocular reconstruction methods.

Yubo ZHAO, Yujin Chai, Yunao Dong, Chengfeng Zhao and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 13 of 20 reviewers recommend it
lenient 5/5
medium 8/10
strict 0/5
70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026KAISTKorea Telecom ResearchKorea Advanced Institute of Scie3D vision & reconstruction

DySurface: Consistent 4D Surface Reconstruction via Bridging Explicit Gaussians and Implicit Functions

DySurface bridges explicit dynamic Gaussians and implicit SDFs via voxel guidance to reconstruct temporally consistent, watertight 4D surfaces.

Minje Kim, Younghyun Noh, Jaesoon Kim, Tae-Kyun Kim

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
5/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 5 of 20 reviewers recommend it
lenient 2/5
medium 3/10
strict 0/5
71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026YonseiNVIDIAYonsei University / Facebook3D vision & reconstruction

RelationVGGT : Visual Geometry Transformers for 3D Spatial Relation Segmentation

RelationVGGT enables feed-forward 3D spatial relation segmentation across multi-view images without camera poses or category names by combining visual semantics with geometry-aware representations via a relation transformer.

Minsu Kim, Jaesung Choe, Jiwoo Lee, Frank Wang and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U MinnesotaTexas A&MTexas A&M University - ColleU Minnesota - Twin CitiesStanford3D vision & reconstruction

DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax

DarkVGGT uses physics-aware thermal modeling and geometry-shared routing to boost feed-forward 3D reconstruction in darkness without impairing daylight performance.

Minseong Kweon, Wenyuan Zhao, Nuo Chen, Lulin Liu and 5 more

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

89%Must read
?Must readVote to see the score
NeurIPS 2026MetaZhejiangFacebookVanderbiltU Pennsylvania3D vision & reconstruction

Knowledge Transfer Scaling Laws for 3D Medical Imaging

Medical imaging pretraining reveals asymmetric cross-domain scaling and power-law transfer, yielding optimized data allocations with a hub-and-island structure that improves transfer over proportional sampling by up to 58%.

Ho Hin Lee, Dongna Du, Chu Wang, Yuankai Huo and 3 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

71%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ETH ZurichU StuttgartETHZ - ETH Zurich3D vision & reconstruction

CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction

CLoSeR detects loop candidates via global descriptors to close loops in streaming reconstruction, reducing drift and producing consistent kilometer-scale geometry with SE(3) pose optimization.

Moyang Li, Zihan Zhu, Wei Zhang, Marc Pollefeys and 1 more

Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
7/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

74%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Sun Yat-senSUN YAT-SEN UNIVERSITYPekingPeng Cheng LaboratoryPengcheng Laboratory3D vision & reconstruction

CodecSplat: Ultra-Compact Latent Coding for Feed-Forward 3D Gaussian Splatting

CodecSplat encodes 2D Gaussian-generation features into compact entropy-coded bitstreams to achieve order-of-magnitude smaller feed-forward 3D Gaussian splatting representations at high PSNR with controllable rate-distortion tradeoffs.

Pengpeng Yu, Runqing Jiang, Qi Zhang, Dingquan Li and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
9/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026City University of Hong Kong3D vision & reconstruction

FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views

FRUC enables feedforward, calibration-free dynamic 3D Gaussian reconstruction from uncalibrated multi-vehicle views via an ego-centric occlusion field and residual cross-agent fusion, achieving state-of-the-art rendering quality and efficiency.

Yihang Tao, Yu Guo, Zhengru Fang, Haonan An and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 3/5
medium 7/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Nanyang TechnologicalZhejiangNTU CCDSByteDance SeedU Adelaide3D vision & reconstruction

Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video

SAGE adapts 3D geometric foundation models via weak Internet video supervision, reducing zero-shot Chamfer Distance by 20, 42% on unseen benchmarks.

Zihui Gao, Ke Liu, Jiawang Bian, Donny Y. Chen and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read
?Must readVote to see the score
NeurIPS 2026NVIDIAU Pennsylvania, University of PeSanta Clara3D vision & reconstruction

Physical AI Smart Spaces: A Large-Scale Benchmark for Multi-Camera 3D Perception in Smart Spaces

Physical AI Smart Spaces introduces multi-camera 3D perception benchmarks for indoor smart spaces spanning synthetic and real-world data, plus 3D HOTA evaluation.

Yuxing Wang, Yizhou Wang, Anqi Li, Shuo Wang and 12 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

83%Must read
?Must readVote to see the score
NeurIPS 2026KeioSB Intuitions3D vision & reconstruction

DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers

DPPE decouples rotation and translation in camera positional encoding to fix training stagnation when scaling multi-view transformers and improves extrapolation.

Shun Kenney, Teppei Suzuki

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
13/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

70%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Ecole Nationale Supérieure de TeENSTA ParisAMIAD3D vision & reconstruction

SS3D: End2End Self-Supervised 3D from Web Videos

SS3D pretrains a feed-forward monocular 3D estimator via web-scale SfM self-supervision, achieving strong zero-shot cross-domain depth, ego-motion, and intrinsics prediction.

Marwane Hariat, Gianni Franchi, David Filliat, Antoine Manzanera

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
5/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

88%Must read
?Must readVote to see the score
NeurIPS 2026Beijing Academy of Artificial InShanghai JiaotongU Electronic Science and TechnolHainanThe Hong Kong University of Scie3D vision & reconstruction

Focusable Monocular Depth Estimation

FocusDepth uses spatially-aligned multi-scale prompt fusion to boost target-region depth accuracy and sharp boundaries while preserving global geometry, outperforming global baselines on FDE-Bench.

Yuxin Du, Tao Lin, Zile Zhong, Runting Li and 6 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
15/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

80%Must read
?Must readVote to see the score
NeurIPS 2026Kyung HeeKyunghee3D vision & reconstruction

Towards Generalizable 3D Anomaly Detection via Relational Inconsistency Modeling

Relational inconsistency modeling defines defects as violated geometric consistency among neighboring structures, improving 3D anomaly detection across domains.

KunHo Heo, SuYeon Kim, Hayoung Lee, Chanse Oh and 1 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

86%Must read
?Must readVote to see the score
NeurIPS 2026U North Carolina at Chapel HillSun Yat-sen University of North Carolina at3D vision & reconstruction

RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection

RefineAny3D treats monocular 3D depth refinement as visual alignment via categorical vision-language action tokens, boosting detectors without numerical regression.

Zhihao Zhang, Gengwei Zhang, Tianlong Chen, Xiaoming Liu

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 14 of 20 reviewers recommend it
lenient 4/5
medium 8/10
strict 2/5
91%Must read
?Must readVote to see the score
NeurIPS 2026City University of Hong KongCity University of Hong KongCity University of Hong Kong3D vision & reconstruction

One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction

DUST uses decoupled dual-timeline Gaussian scene graphs for asynchronous vehicle-infrastructure 4D reconstruction, cutting ghosting to boost dynamic-area PSNR by 3.2 dB.

Yulong Chen, Xiaoyun Dong, Haoyu Zhang, Zongxian Yang and 5 more

Paris Poster Session 5, Fri, Dec 11, 11:30 AM–1:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
17/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026U OxfordU CambridgeComputer Science Department, StaNanyang TechnologicalMeta and University of Oxford3D vision & reconstruction

Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control

Instruct-Particulate predicts articulated 3D part segmentation and joint parameters from meshes and kinematic specifications, scaling training via vision-language labels to improve cross-category and AI-generated mesh generalization.

Ruining Li, Yuxin Yao, Matt Zhou, Chuanxia Zheng and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 5/5
medium 5/10
strict 0/5
80%Must read
?Must readVote to see the score
NeurIPS 2026Comenius University in BratislavCzech Technical Univeresity in PSoutheastCIIRC, Czech Technical UniversitCzech Technical University in Pr3D vision & reconstruction

Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth

Depth2Pose evaluates monocular depth estimators via downstream pose estimation accuracy using only camera poses, introducing a challenging out-of-distribution benchmark where standard metrics fail to predict generalization.

Viktor Kocur, Sithu Aung, Gabrielle Flood, Yaqing Ding and 3 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
12/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

Show 20 more papers