Full Description
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 29-October 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.
Contents
Audio-Synchronized Visual Animation.- Expressive Whole-Body 3D Gaussian Avatar.- Canonical Shape Projection is All You Need for 3D Few-shot Class Incremental Learning.- Controllable Human-Object Interaction Synthesis.- High-Fidelity and Transferable NeRF Editing by Frequency Decomposition.- DoughNet: A Visual Predictive Model for Topological Manipulation of Deformable Objects.- PAV: Personalized Head Avatar from Unstructured Video Collection.- Strike a Balance in Continual Panoptic Segmentation.- In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation.- MultiDelete for Multimodal Machine Unlearning.- Unified Local-Cloud Decision-Making via Reinforcement Learning.- UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model.- Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation.- Efficient Frequency-Domain Image Deraining with Contrastive Regularization.- Stitched ViTs are Flexible Vision Backbones.- TrajPrompt: Aligning Color Trajectory with Vision-Language Representations.- SemReg: Semantics Constrained Point Cloud Registration.- Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views.- RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception.- ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer.- Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting.- AlignDiff: Aligning Diffusion Models for General Few-Shot Segmentation.- SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition.- R^2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding.- Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors.- Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering.- DomainFusion: Generalizing To Unseen Domains with Latent Diffusion Models.
