Computer Vision – ECCV 2024

Diffusion Models as Optimizers for Efficient Planning in Offline RL.- Enhanced Sparsification via Stimulative Training.- How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs.- NeuroPictor: Refining fMRI-to-Image Reconstruction via  Multi-individual Pretraining and Multi-level Modulation.- Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image.- Efficient Snapshot Spectral Imaging: Calibration-Free Parallel Structure with Aperture Diffraction Fusion.- Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective.- PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking.- HiDiffusion:  Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models.- On the Approximation Risk of Few-Shot Class-Incremental Learning.- Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach.- Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization.- SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning.- Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning.- MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation.- PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training.- General Geometry-aware Weakly Supervised 3D Object Detection.- Long-CLIP: Unlocking the Long-Text Capability of CLIP.- Dolfin: Diffusion Layout Transformers without Autoencoder.- Real-time 3D-aware Portrait Editing from a Single Image.- StructLDM: Structured Latent Diffusion for 3D Human Generation.- Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation.- Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models.- Norma: A Noise Robust Memory-Augmented Framework for Whole Slide Image Classification.- Continuous Memory Representation for Anomaly Detection.- InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser.- PACE: Pose Annotations in Cluttered Environments.