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; object recognition; motion estimation.

Inhalt

Neural Metamorphosis.- WHAC: World-grounded Humans and Cameras.- Federated Learning with Local Openset Noisy Labels.- Diff3DETR: Agent-based Diffusion Model for Semi-supervised 3D Object Detection.- PSALM: Pixelwise Segmentation with Large Multi-modal Model.- Layout-Corrector: Alleviating Layout Sticking Phenomenon in Discrete Diffusion Model.- Active Coarse-to-Fine Segmentation of Moveable Parts from Real Images.- Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture.- Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities.- Kinetic Typography Diffusion Model.- Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction.- Light-in-Flight for a World-in-Motion.- GroupDiff: Diffusion-based Group Portrait Editing.- Faceptor: A Generalist Model for Face Perception.- Inter-Class Topology Alignment for Efficient Black-Box Substitute Attacks.- Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels.- InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping.- KDProR: A Knowledge-Decoupling Probabilistic Framework for Video-Text Retrieval.- Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images.- Learning with Unmasked Tokens Drives Stronger Vision Learners.- Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken.- Multi-Task Domain Adaptation for Language Grounding with 3D Objects.- Efficient Active Domain Adaptation for Semantic Segmentation by Selecting Information-rich Superpixels.- Efficient Training of Spiking Neural Networks with Multi-Parallel Implicit Stream Architecture.- Camera-LiDAR Cross-modality Gait Recognition.- LiteSAM is Actually what you Need for segment Everything.- IGNORE: Information Gap-based False Negative Loss Rejection for Single Positive Multi-Label Learning.