Building Rome from a Single Image

A redesigned object-centric generator partitions scenes into distance-adaptive chunks, captures 2D-3D correspondence, and trains on 4,000 outdoor scenes to outperform baselines in indoor and outdoor mesh generation.

Jiraphon Yenphraphai, Fang Li, Tianshuo Xu, Depu Meng and 4 more

Published Oct 6, 2026 · ▲ 4 on Hugging Face

DistScene: Object-to-Scene Distillation for 3D Scene Generation

DistScene generates compositional 3D scenes from single images via object-to-scene distillation, improving spatial coherence by modeling environments as explicit components with shared coordinate frames.

Kunming Luo, Hongyu Yan, Ken Deng, Chengcheng Zhou and 5 more

Published Oct 3, 2026 · ▲ 4 on Hugging Face

EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling

EditHero benchmarks long-horizon part-level 3D editing via sequential instructions and target images, finding agentic code-based methods preserve unedited regions better but are slower than non-agentic regeneration.

Ruihan Yu, Yu-Ju Tsai, Muyao Niu, Runyi Li and 8 more

Published Oct 1, 2026 · 0 citations · ▲ 50 on Hugging Face · Code ★ 12

ABot-Earth 0.5: Generative 3D Earth Model

ABot-Earth 0.5 generates seamless 3D environments from satellite imagery via 3D Gaussian Splatting, synthesizing square kilometers in under 10 minutes with real-time web visualization and embodied AI navigation support.

Ming Qian, Tianjian Ouyang, Mingchao Sun, Zijian Wang and 24 more

Published Jun 8, 2026 · 0 citations · ▲ 177 on Hugging Face · Code ★ 222

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Lyra distills video diffusion models into explicit 3D Gaussian splatting via self-distillation, enabling text- or image-conditioned static and dynamic 3D scene generation without multi-view training data.

Sherwin Bahmani, Tianchang Shen, Jiawei Ren, Jiahui Huang and 9 more

Published Sep 23, 2025 · 0 citations · ▲ 32 on Hugging Face · Code ★ 2,638

MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation

Zhiqi Li, Wenhuan Li, Tengfei Wang, Zhenwei Wang and 7 more

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

BLARM: Animating 3D Objects from Video via Blending LAtent Rigid Motion Primitives

Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang and 5 more

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

Pygmalion: Bridging Reconstruction and Generation in Sparse Voxel-based 3D Modeling

Guan Luo, Jing Lin, Xuanyu Yi, Jiahang Liu and 2 more

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

FogGS: Physics-Grounded 3D Foggy Effects

Jiaxin LI, Tailin Wu, Jiankang Deng, Li Zhang and 1 more

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

3D Molecule Generation from Rigid Motifs via $\mathrm{SE}(3)$ Flows

Roman Poletukhin, Marcel Kollovieh, Eike S. Eberhard, Stephan Günnemann

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

PRISM: Programming Interactive Scenes from Monocular Images for Embodied Simulation

Yumeng He, Yichen Song, Xiaotian Yang, Weijia Zhang and 4 more

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

3D Consistency Tokens

Seungtae Nam, Jungwoo Kim, Gyeongjin Kang, Younggeun Lee and 2 more

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

The Fault in Our Metrics: Revisiting Generative Model Evaluation with Chamfer Distance

Chirag Vashist, Vaibhav Santhosh, Tristan Engst, Yanshu Zhang and 1 more

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

Spatially Feasible 3D Indoor Scene Generation via Interaction-Oriented Human Proxy

Xinyuan Chen, Mingwen Shao, Qiao Zhang, Qinglin Zhan and 7 more

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

Geometry-Centered 3D Latent World Models for Growing Surfaces

Xiaoyi Liu, Hao Tang

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Blur Issue Matters for Thermal Novel View Synthesis: A Floating Gaussian Suppression Approach

Mingyuan Xie, Sheng Wan, Jin Xie, Hang Yang and 2 more

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

LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance

Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li and 9 more

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

Plan4D: Generative Plannable 4D Worlds

Hangwei Zhang, Rujing Dang, Ruimin Lin, Jiahong Wu and 2 more

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

Intent2CAD: How Semantic-Parametric Supervision Shapes Text-to-CAD Generation

Jinbo Yang, Shikai Jing, Mingyue Yuan

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

HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection

Weilin Sun, Lei Meng, Lihui Zhang, Manyi Li and 1 more

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

AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation

Tracy Han, Lulin Liu, Bangya Liu, Yuanhao Cai and 7 more

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

Trivialized Generative Models on Lie Groups

Neil He, Meenal Jhajharia, Qianxi Wu, Chaoran Cheng and 2 more

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

StoSplat: Ray-Aligned Stochastic Preconditioning for Feed-Forward 3D Gaussian Splatting

Qibin Hu, Zhiheng Fu, Longguang Wang, Jisheng Dang and 2 more

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

GeoWorld: A Geometry-First World Model for Reconstruction and Imagination

Baicheng Li, Jialin Liu, Dong Wu, Weijian Xie and 6 more

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

TESLA: Native 4D Gaussian Splatting Generation with Temporally Structured Latents

Weiqi Zhang, Junsheng Zhou, Juntong Fang, Kanle Shi and 2 more

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

Pose-Free Feed-Forward 3D Inpainting via Learnable Mask Attention and Support Token Refinement

Jingyi Pan, Dan Xu, Qiong Luo

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

LoopNav: Benchmarking Spatial Consistency in World Models

Kewei Lian, Shaofei Cai, Yitao Liang, Anji Liu

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

A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

Dongxu Wei, QiXu, Zhiqi Li, Hangning Zhou and 5 more

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

DiDE: Direct Injection with Color-Texture DEcoupling for 3D Stylization

Tao Wu, Alexandra Gomez-Villa, Senmao Li, Yaxing Wang and 2 more

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

Efficient and Robust Physical 3DGS-MPM Simulation via Interior Filling and Text-Physics Optimization

Yikun Ma, Yiqing Li, Jingwen Ye, Zhongkai Wu and 3 more

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

Intrinsic-Preserving Schrödinger Bridge for Direct Part-Aware 3D Generation

Qitong Yang, Mingtao Feng, Zijie Wu, Jie Feng and 2 more

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

ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation

Minh Tu, Quang-Binh Nguyen, Khoi Nguyen

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

Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed Generation

Yiqun Zhao, Binbin Huang, Haobin Duan, Zibo Zhao and 1 more

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

Generative Structure from Motion with Native 3D Diffusion

Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao and 3 more

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

HoloCode: A Code-Centric Multi-Agent Framework for Image-to-3D Scene Generation

Hanlin Chen, Chung-Ching Lin, Yuyang Zhao, Dongyue Lu and 6 more

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

StructBridge: Structure-Grounded 3D Indoor Object Generation via 3D Latent Diffusion Bridge and Normal Refinement

Nange Wang, Zhanxu Bai, Yuxuan Li, Cewu Lu and 1 more

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

ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation

Tzu-Hsin Hsieh, Ricardo Marroquim

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

Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models

Aniket Kriplani, Yiwen Zhang, Angelina Wang, Hadar Averbuch-Elor

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes

WorldAct converts static generated 3D worlds into editable, interaction-ready scenes via multimodal decomposition and object reconstruction to enable manipulation and embodied tasks.

Jichen Hu, Jiawei Guo, Jiazhong Cen, Chen Yang and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 5 on Hugging Face · Code ★ 32

Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation

Rigel3D generates animation-ready 3D assets with coupled geometry and skeleton latents, outperforming post-hoc rigging baselines across metrics.

Nikitas Chatzis, Marios Loizou, Evangelos Kalogerakis

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

URDF-Anything+: End-to-End Generation for Simulation-Ready Articulated Assets

URDF-Anything+ directly generates simulation-ready articulated URDF models from single RGB images via end-to-end autoregressive diffusion, outperforming prior methods in reconstruction quality, joint estimation, and physical executability.

Zhuangzhe Wu, Yue Xin, Chengkai Hou, Minghao Chen and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face

Enhancing Novel View Synthesis via Geometry Grounded Set Diffusion

SetDiff integrates explicit 3D geometry priors into a set-based diffusion model to improve novel-view synthesis from 3D Gaussian Splatting, reducing hallucinations and achieving state-of-the-art results.

Farhad G. Zanjani, Herbert Cai, Amirhossein Habibian

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

Text-to-CAD Evaluation with CADTests

CADTestBench introduces executable software tests to evaluate text-to-CAD models via geometric and topological requirements, showing test-guided baselines surpass current methods.

Dimitrios Mallis, Marco Wang, Ahmet Karadeniz, Elisa Ricci and 2 more

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

Seeing Speech: Learning Visible Articulatory Dynamics for Speech-Driven 3D Facial Animation

The framework models visible speech via directional articulatory motions composed into 3D facial animation, improving lip articulation and realism over prior methods.

Hyung Kyu Kim, Byungchan Hwang, HAKGU KIM

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

Velocity-Space 3D Asset Editing

VS3D performs local 3D asset editing inside the ODE sampler via three modules that eliminate identity leakage and amplify edits without masks or training.

Hao Liu, yuxuan lin, jingfeng Guo, Ruihang Chu and 3 more

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

LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators

LiFT generates high-resolution 3D medical images via inter-slice feature trajectories, achieving strong coherence with much lower inference cost.

Xinhe Zhang, Yuyang Zhang, Pengfei Jin, Arnau Marin-Llobet and 2 more

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

SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation

SILSA generates high-resolution 3D shapes with sliding-window slice latents and slice-level topology supervision to improve fidelity, reduce tokens by over 70%, and lower inference time by 58.5%.

Tianjiao (Joey) Yu, Xinzhuo Li, Yifan Shen, Ying Shen and 3 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 37 on Hugging Face

One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation

Monocular pretraining lifts single images into pseudo-target views via depth and reprojection, yielding OVIE, which rivals multi-view baselines at 116 FPS without inference-time depth or multi-view training pairs.

Adrien RAMANANA RAHARY, Nicolas Dufour, Patrick Perez, David Picard

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 5 on Hugging Face · Code ★ 82

Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation

Seg3DParts uses segmentation-grounded generation with structured cross-part interaction to produce controllable, coherent part-level 3D meshes from single images while introducing the PartObjectNet dataset.

Jiantao Lin, Meixi Chen, Yingjie Xu, Chenbo FU and 4 more

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

SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology

SAMoR encodes cross-topology articulated motion into shared part tokens via graph-transformer encoding and attention supervision, achieving 5.8× lower reconstruction error than adapted baselines across arbitrary skeletons.

Yuhao Zhang, Gerard Pons-Moll, Tolga Birdal

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

Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation

BDF transforms mesh connectivity into continuous surface signals for diffusion models, enabling higher-quality, scalable native 3D mesh generation.

Gaochao Song, Haohan Weng, Luo Zhang, Zibo Zhao and 1 more

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

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

VideoMDM trains 3D human motion diffusion models solely from 2D video poses via depth-weighted reprojection, nearly matching fully 3D-supervised quality without ground-truth 3D data.

Amir Mann, Gal M Harari, Merav keidar, Or Litany

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 22 on Hugging Face · Code ★ 58

Fast 4D Mesh Generation by Spatio-Temporal Attention Chains

Spatio-Temporal Attention Chains accelerate training-free 4D mesh generation 13x to 9 seconds via latent temporal correspondences, improving quality, scaling to longer videos, and enabling tracking and camera estimation.

Dvir Samuel, Yuval Atzmon, Gal Chechik, Yoni Kasten

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 11 on Hugging Face

Dream-Cubed: Controllable Generative Modeling in Minecraft by Training on Billions of Cubes

Dream-Cubed introduces a billion-scale Minecraft voxel dataset and diffusion models that generate interactive 3D worlds directly from block tokens with inpainting and outpainting support.

Tim Merino, Sam Earle, Ryunosuke Iwai, Julian Togelius and 1 more

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

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation

Articraft uses LLM agents to programmatically generate validated articulated 3D assets at scale, yielding 10K assets for training and simulation.

Matt Zhou, Ruining Li, Xiaoyang Lyu, Zhaomou Song and 5 more

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

Toward Better Geometric Representations for Molecule Generative Models

LENSEs improves representation-conditioned molecule generation via multi-level heads, perceptual loss, and node-level alignment, achieving 97.28% validity and 98.51% stability on GEOM-DRUG.

Shaoheng Yan, Zian Li, Cai Zhou, Qiaojing Huang and 2 more

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