Computer Vision – ECCV 2026

Kirin: Animal Motion Generation from In-the-Wild Video.- Dynamic World Generation Made Efficient.- Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models.- WARP: Wide Attention with Rich Projections for Image Super-Resolution.- Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models.- Adapting MLLMs for Nuanced Video Retrieval.- Leaving the City: A Large-Scale Aerial Dataset for Cross-Season Localization in Unstructured Environments.- Triangular Consistency as a Universal Constraint for Learning Optical Flow.- NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment.- PyraE2E: Enhancing End-to-End WSI Analysis via Cross-Scale Super-Resolution.- Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space.- ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling.- Detecting Backdoors in Object Detection via Pre-NMS Prediction Distribution Shift.- BEVLM: Distilling Semantic Knowledge from LLMs into Bird’s-Eye View Representations.- Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment.- ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving.- MixCompress: Mixture of Experts for Variable Rate Learned Image Compression.- LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension.- VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM.- Curvature-Guided Mixing for MLLM Adaptation.- SAEdit: Token-Level Control for Continuous Image Editing via Sparse Autoencoder.- UNet-Twice: A Simple Structured Reference-based Inpainting Framework.- RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing.- A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP.- FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI.- HOIMask: Towards Generative Masked Modeling for Human Object Interaction Generation.- Beyond Attention: Convolutional Global Context for Remote Sensing Change Detection.- DPGS: A Diffusion-Prior Guided Framework for Large-Scale 3D Gaussian Splatting Reconstruction.- Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models.- ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution.- 340 FPS Reflection-free Video from Spikes Modulated by a Rapidly Rotating Polarizer.- Spatial Amsan: A Benchmark for Perception-Grounded Spatial Reasoning and Action Evaluation in Egocentric Manipulation.- Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration.- SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation.- Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation.- DOGE: Differentiable Bézier Graph Optimization for Road Network Extraction.- VTEdit-Bench: A Comprehensive Benchmark for Multi-Reference Image Editing  Models in Virtual Try-On.