JLD: Perceptual Distance Through A Jacobian Lens

JLD defines a perceptual image distance via a Jacobian-derived metric tensor from frozen vision encoders, achieving state-of-the-art correlation with human judgments and resolution robustness.

Shreshth Saini, Balu Adsumilli, Alan C. Bovik

Published Oct 5, 2026 · ▲ 3 on Hugging Face · Code ★ 3

GeoMamba: Geometry-Aware State Space Modeling for Image Restoration

Dafeng Zhang, Shizhuo Liu

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

PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image Fusion

Rui Liu, Lin Gu, Hesong Li, Ying Fu

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

Discovering Unseen Degradations to Adapt Open-World Image Restoration

Boseong Kim, Tae Hyun Kim, Donghyeon Cho

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

Beyond MSE: Differentiable Complexity Priors for Structure-Preserving Neural Denoising

Xiangyu Jiang, Jie Huang

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

PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation

Beibei Lin, Tingting Chen, Xin Zhang, Wenhao Zhao and 2 more

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

Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement

Wei Zhu, Kai Zhang, Yu Zheng, Lei Luo and 2 more

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

Joint EM Image Super-Resolution and Segmentation with Semantic and Structural Priors

Jiateng Shou, Haoyuan Shi, Zhiwei Xiong

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

Exploring the Epipolar Consistency for Light Field Deraining

Chen Gao, Youfang Lin, Wenbin Wang, Shuo Zhang

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

Real-World Dual-Pixel Raindrop Removal: A New Benchmark and Degradation-Adaptive RWKV Baseline

Hao Yang, Ruikun Zhang, Liyuan Pan

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

Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging

Sichen Wang, Zhipeng Lu

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

Bridging Image Restoration and Recognition via Causal Mediated Unrolling

Haowei Li, Qing Zhao, Yanze Li, ZhiChen Chen and 3 more

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

WorldSR: Harnessing World Knowledge Search for Grounded Image Super-Resolution

Junyuan Deng, Xinyi Wu, Zhenyao Wu, Song Wang and 2 more

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

Matching2Matching: Zero-Shot Light Field Image Denoising with Matching View Construction

Shuo Zhang, Qian Tian, Chen Gao, LongzhaoGuo and 1 more

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

Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning

Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim

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

All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow

Wei Dong, Han Zhou, Terry Ji, Guanhua Zhao and 5 more

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

DoFP-Aligned Lookup Tables for Real-Time Polarization Demosaicking

Yidong Luo, Chenggong Li, Yunfeng Song, Mengyuan Liu and 2 more

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

Noise-Regularized Training for Learned Image Compression

Renjie Zou, Zhiwei Huang, Dong Jiang

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

Reliability-Budgeted Edge–Cloud Adaptation for Continual Multimodal Dehazing on UAV

Junwei Zhao, Qianchun Luo, Jie Wu

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

Beyond Unidirectional: Unsupervised Trajectory Learning for Omnidirectional Controllable Underwater Image Enhancement

Xiaofeng Cong, Xuhao Guo, Kang Zheng, Yu-Xin Zhang and 1 more

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

CoScan: Multi-Scale Content-Adaptive Space-Filling Scans for Causal State-Space Image Restoration

Wei Dong, Terry Ji, Yan Min, Shahram Shirani and 2 more

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

DeGlare: Self-Supervised Specular Removal for Industrial Metallic Surfaces via Multi-Illumination Priors

Bisma Amjad, Henry Wood, William Jacobs, Andrew Mills

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

Learning Motion-Appearance Coupling Priors for Solving Video Inverse Problems

Anselm Krainovic, Reinhard Heckel

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

Not All Noise Is Harmful: Towards Perception Aware and Controllable RAW Image Joint Denoising and Demosaicing

Qianjun Huang, Qingguo Liu, Hui Zeng, Kai Zhang and 1 more

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

PhysRemover: A Unified Framework for Physically Realistic Object Removal

Dongxu Yue, Weixuan Jin, Yuhang Yu, Bo Li and 7 more

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

PhysDNet: Physics-Driven Gradient Amplification for Real-Time Image Dehazing

Rayen Dhahri, Lei Sun, Victor J Morinigo, Alice Pagnoux and 3 more

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

Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

Jinwoo Chung, Jangho Kim

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

Do Image Editing Models Understand Lighting?

Tim Küchler, Johann-Friedrich Feiden, Matthias Niessner, Carsten Rother

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

Zero-Shot Burst Restoration via Diffusion MAP Inference with Poisson-Gaussian Noise Likelihood

Ziyao Yi, Luca Savant Aira, Diego Valsesia, Tiziano Bianchi and 1 more

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

Decoupling Direction and Magnitude: Language-Steered Flow Matching for Super-Resolution in the Dark

Jiaxin Gao, Ziyu Yue, Yaohua Liu, Danchen Cui and 2 more

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

MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement

Ruodai Cui, Shuaizheng Liu, Rongyuan Wu, Lei Zhang

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

PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing

PRISM proposes a unified physically structured framework for real-world dehazing via proximal scattering atmosphere reconstruction, online non-uniform haze synthesis, and selective self-distillation adaptation to achieve competitive restoration results.

Chengyu Fang, Chunming He, Yuelin Zhang, Chubin Chen and 5 more

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

CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators

CHASM shares a learned channel eigenbasis across frequencies while keeping frequency-specific gains, consistently improving spectral token mixers in MRI and image reconstruction.

Pengcheng Fang, Hongli Chen, Yuxia Chen, Tengjiao Sun and 2 more

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

QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems

QUTCC trains a U-Net for spatially adaptive quantile regression and calibrates tighter pixel-valid uncertainty intervals via non-linear conformal scaling for imaging inverse problems.

Cassandra T Ye, Shamus Li, Tyler King, Kristina Monakhova

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

ODDR: One-Step Deshadow Diffusion via Reward Guidance

ODDR achieves efficient, high-fidelity shadow removal without real-world paired supervision via one-step diffusion guided by a synthetic, annotation-free ShadowReward model, approaching fully supervised performance.

Junseong Shin, Kijun Kim, Minseong Kim, Dongjin Kim and 1 more

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

PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video

PickMoment learns continuous-time blur integration via sub-interval mean predictions with additivity and sharp-frame constraints to unify deblurring and video generation in one pass.

Junseong Shin, Hyeonsu Jo, Daehyun Kim, Tae Hyun Kim

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

SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation

SR-Prominence defines artifact prominence via crowdsourced annotations across 3,935 masks and shows classical full-reference metrics surprisingly detect perceptual impact better than specialized detectors.

Ivan Molodetskikh, Kirill Malyshev, Mark Mirgaleev, Nikita Zagainov and 2 more

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

GLUT: 3D Gaussian Lookup Table for Continuous Color Transformation

GLUT represents color transformations with learnable 3D Gaussian primitives for continuous, explicit, compact, and locally editable LUTs.

Danna Xue, David Serrano-Lozano, Shaolin Su, Javier Vazquez-Corral

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

Single Shot HDR Recovery via a Video Diffusion Prior

By recasting single-shot HDR reconstruction as video diffusion of exposure brackets fused by a lightweight UNet, it achieves high input fidelity and outperforms generative baselines on benchmarks and in 72% of human comparisons.

Chinmay Talegaonkar, Jinshi He, Nicholas Antipa

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

Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration

Continuous Expert Assembly uses instance-conditioned low-rank residuals for token-wise dynamic parameterization to improve all-in-one image restoration, particularly for spatially varying and compositional degradations.

Haisen He, XIANGYU ZOU, SongLin Dong, Heng Li and 2 more

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

FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution

FluxFlow uses conservative flow matching with observation uncertainty and Wiener-regularized correction for ground-to-space astronomical super-resolution, outperforming baselines on real DESI-HST pairs.

Shuhong Liu, Xining Ge, quanfeng xu, Ziteng Cui and 8 more

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

AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark

AbsoluteDegradation synthesizes realistic film degradations via physics-inspired modular pipelines and introduces a large-scale archival benchmark, showing improved real-world generalization and exposing current restoration failure modes.

Mikołaj Jastrzębski, Dawid Glinkowski, Dawid Zieliński, Daniel Borkowski and 2 more

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

A Principled Self-Referenced Early Stopping Approach for Deep Image Prior

Proposed pseudo self-referenced early stopping for Deep Image Prior uses constructed image pairs to detect overfitting, outperforming existing methods across inverse imaging problems without requiring noise level estimates.

Chaoyan Huang, Cheng-Han Huang, Ismail Alkhouri, Rongrong Wang

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

SkipSR: Faster Super-Resolution with Token Skipping

SkipSR accelerates diffusion video super-resolution by skipping low-detail regions identified in low-resolution inputs, achieving up to 60% faster latency without quality loss.

Rohan Choudhury, Shanchuan Lin, Jianyi Wang, Hao Chen and 5 more

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

IRPO: Boosting Image Restoration via Post-training GRPO

IRPO applies GRPO post-training to image restoration via selective hard-sample data and multi-component rewards, improving in-domain accuracy by 0.93 dB and OOD generalization by 3.43 dB.

Haoxuan Xu, Yi Liu, Tianfu Li, Ruolin Shen and 6 more

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

Improving Diffusion Posterior Samplers with Lagged Temporal Corrections for Image Restoration

LAMP improves diffusion posterior samplers via second-order lagged temporal corrections that reduce reverse dynamics variability, yielding consistent gains over DiffPIR and DDRM without extra denoising steps.

Davide Evangelista, Elena Morotti, Francesco Pivi, Maurizio Gabbrielli

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

i-DEQ: A stable inertial Deep Equilibrium model for image restoration

i-DEQ uses momentum in deep equilibrium fixed-point iterations for stable, accelerated image restoration with convergence guarantees and twofold faster inference.

Antonin Clerc, Marien Renaud, Baudouin Denis de Senneville, Nicolas Papadakis

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

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

AVIS uses autoregressive diffusion for streaming video inverse problems, cutting latency from 114s to 4s and boosting throughput to 1.18 FPS with better quality, while AVIS Flash reaches 5.91 FPS.

Taesung Kwon, Jonghyun Park, Hyungjin Chung, Jong Chul Ye

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

LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing

LiBrA-Net predicts low-resolution bilateral affine grids fused via Lie-algebraic regularization for real-time 4K video dehazing, and introduces the UHV-4K benchmark.

Yongcong Wang, Chengchao Shen, Guangwei Gao, Wei Wang and 4 more

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

Probing Visual Planning in Image Editing Models

EAR reformulates visual planning as single-step editing and evaluates it on abstract maze puzzles, showing models fail zero-shot but generalize via finetuning yet remain below human efficiency.

Zhimu Zhou, Yanpeng Zhao, Qiuyu Liao, Bo Zhao and 1 more

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