Computer Vision - ECCV 2024

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance.- Localization and Expansion: A Decoupled Framework for Point Cloud Few-shot Semantic Segmentation.- Think before Placement: Common Sense Enhanced Transformer for Object Placement.- Oulu Remote-photoplethysmography Physical Domain Attacks Database (ORPDAD).- Leveraging Imperfect Restoration for Data Availability Attack.- 3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance.- Open-set Domain Adaptation via Joint Error based Multi-class Positive and Unlabeled Learning.- DoubleTake: Geometry Guided Depth Estimation.- Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL.- Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting.- Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models.- Edge-Guided Fusion and Motion Augmentation for Event-Image Stereo.- MetaWeather: Few-Shot Weather-Degraded Image Restoration.- CPT-VR: Improving Surface Rendering via Closest Point Transform with View-Reflection Appearance.- Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition.- HiFi-123: Towards High-fidelity One Image to 3D Content Generation.- Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View.- Good Teachers Explain: Explanation-Enhanced Knowledge Distillation.- Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation.- FRDiff : Feature Reuse for Universal Training-free Acceleration of Diffusion Models.- Möbius Transform for Mitigating Perspective Distortions in Representation Learning.- TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection.- CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction.- SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments.- OpenDistill3D: Open-World 3D Instance Segmentation with Unified Self-Distillation for Continual Learning and Unknown Class Discovery.- DiffCD: A Symmetric Differentiable Chamfer Distance for Neural Implicit Surface Fitting.- Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking.