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. The papers 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

Tri^{2}-plane: Thinking Head Avatar via Feature Pyramid.- ControlCap: Controllable Region-level Captioning.- Free Lunch for Gait Recognition: A Novel Relation Descriptor.- SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding.- Adaptive Correspondence Scoring for Unsupervised Medical Image Registration.- MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models.- Watch Your Steps: Local Image and Scene Editing by Text Instructions.- Forget More to Learn More: Domain-specific Feature Unlearning for Semi-supervised and Unsupervised Domain Adaptation.- 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences.- Idea2Img: Iterative Self-Refinement with GPT-4V for Automatic Image Design and Generation.- Human-in-the-Loop Visual Re-ID for Population Size Estimation.- SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation.- PointNeRF++: A multi-scale, point-based Neural Radiance Field.- A Semantic Space is Worth 256 Language Descriptions: Make Stronger Segmentation Models with Descriptive Properties.- UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding.- Fast View Synthesis of Casual Videos with Soup-of-Planes.- Adaptive Human Trajectory Prediction via Latent Corridors.- Video Question Answering with Procedural Programs.- DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification.- TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling.- C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition.- LLMGA: Multimodal Large Language Model based Generation Assistant.- Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos.- Shape from Heat Conduction.- An Adaptive Screen-Space Meshing Approach for Normal Integration.- Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation.- HandDGP: Camera-Space Hand Mesh Prediction with Differentiable Global Positioning.