Computer Vision - ECCV 2024

The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes the refereed proceedings of the 18th European Conference on Computer Vision, ECCV 2024, held in Milan, Italy, during September 29October 4, 2024.

The 2387 papers presented in these proceedings were carefully reviewed and selected from a total of 8585 submissions. They deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; motion estimation.

Inhalt

FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions.- ScanTalk: 3D Talking Heads from Unregistered Scans.- Controllable Navigation Instruction Generation with Chain of Thought Prompting.- GiT: Towards Generalist Vision Transformer through Universal Language Interface.- ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attention.- A Cephalometric Landmark Regression Method based on Dual-encoder for High-resolution X-ray Image.- Exploring the Feature Extraction and Relation Modeling For Light-Weight Transformer Tracking.- LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment.- You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation.- Gaussian Grouping: Segment and Edit Anything in 3D Scenes.- CoMo: Controllable Motion Generation through Language Guided Pose Code Editing.- MegaScenes: Scene-Level View Synthesis at Scale.- SuperGaussian: Repurposing Video Models for 3D Super Resolution.- Towards Model-Agnostic Dataset Condensation by Heterogeneous Models.- Goldfish: Vision-Language Understanding of Arbitrarily Long Videos.- MeshFeat: Multi-Resolution Features for Neural Fields on Meshes.- Decoupling Common and Unique Representations for Multimodal Self-supervised Learning.- MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.- Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation.- 2S-ODIS: Two-Stage Omni-Directional Image Synthesis by Geometric Distortion Correction.- Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models.- D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction.- Combining Generative and Geometry Priors for Wide-Angle Portrait Correction.- RealViformer: Investigating Attention for Real-World Video Super-Resolution.- Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution.- Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation.- UniFS: Universal Few-shot Instance Perception with Point Representations.