Computer Vision – ECCV 2024

ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation.- SINDER: Repairing the Singular Defects of DINOv2.- SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow.- Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation.- General and Task-Oriented Video Segmentation.- VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement.- LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors.- ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback.- TF-FAS: Twofold-Element Fine-Grained Semantic Guidance for Generalizable Face Anti-Spoofing.- Prompting Future Driven Diffusion Model for Hand Motion Prediction.- Defect Spectrum: A Granular Look of Large-scale Defect Datasets with Rich Semantics.- Unveiling Advanced Frequency Disentanglement Paradigm for Low-Light Image Enhancement.- RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation.- UMBRAE: Unified Multimodal Brain Decoding.- NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models.- 3D Single-object Tracking in Point Clouds with High Temporal Variation.- Adaptive Multi-task Learning for Few-shot Object Detection.- Event Trojan: Asynchronous Event-based Backdoor Attacks.- Stepwise Multi-grained Boundary Detector for Point-supervised Temporal Action Localization.- Imaging Interiors: An Implicit Solution to Electromagnetic Inverse Scattering Problems.- Dropout Mixture Low-Rank Adaptation for Visual Parameters-Efficient Fine-Tuning.- OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers.- LoA-Trans: Enhancing Visual Grounding by Location-Aware Transformers.- HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression.- Energy-induced Explicit quantification for Multi-modality MRI fusion.- ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement.- Exemplar-free Continual Representation Learning via Learnable Drift Compensation.