Computer Vision – ECCV 2026

D2PO: Optimizing Diffusion Samplers via Dynamic Preference.- Indelible Backdoors: On the Limits of Post-Training Defenses.- NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation.- Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurring.- BEVOpen3D: Towards Open-World 3D Object Detection in Bird's-Eye-View.- ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models.- Adaptive Neural Dynamics for Robust Geometric LiDAR-Inertial State Estimation on UAVs.- Diffusion Model as a Generalized Segmentation Learner.- Safe Generalization: Mitigating Catastrophic Forgetting in Single-Source Multi-Organ Segmentation via Collaborative Causal Learning.- PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models.- CSS-BA: Gate Guided Column Space Search for Bundle Adjustment.- FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis.- Conditional Flow Matching for Visually-Guided Acoustic Highlighting.- Affordance-Guided Diffusion Prior for 3D Hand Reconstruction.- FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization.- EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing.- DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies.- Progressive Representation Learning for Multimodal Sentiment Analysis with Incomplete Modalities.- Diffusion-Based Immersive Visual Reasoning.- Context-Aware Joint Alignment for Cross-Scene Hyperspectral Image Classification.- SOVTrack: Open-Vocabulary Multi-Object Tracking with Self-Supervised Pseudo Labeling and Feature Distillation.- Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation.- Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability.- ObjectForesight: Predicting 3D Object Trajectories from Human Videos.- Task Alignment: A simple and effective proxy for model merging in computer vision.- Walk through Paintings : Ego-centric World models from Internet Priors.- SEERBench: A Spatial Ego-Exo Reasoning Benchmark for MLLMs with a Simple Yet Effective Baseline.- Revisiting Autoregressive Models for Generative Image Classification.- Towards Reliable Medical Large Vision-Language Models via Counterfactual Preference Optimization.- GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents.- Generative Refinement Network for Visual Synthesis.- Towards Geometry-Grounded Dense Semantic Matching with VGGT Priors.- NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation.- Compact and Structurally Transparent Cervical Cytology with Geometry-Driven Features and Closed-Form Attention.- Wavelet-based Intra-video Counterfactual Reasoning for Video Question Grounding.- FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control.- IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation.