Computer Vision – ECCV 2024 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part XXX

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. 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.

SemanticHuman-HD: High Resolution Semantic disentangled 3D Human Generation.- CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians.- Monocular Occupancy Prediction for Scalable Indoor Scenes.- Visual Grounding for Object-Level Generalization in Reinforcement Learning.- 3DEgo: 3D Editing on the Go!.- Efficient Depth-Guided Urban View Synthesis.- Probabilistic Weather Forecasting with Deterministic Guidance-based Diffusion Model.- Domain-adaptive Video Deblurring via Test-time Blurring.- Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures.- NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving.- OLAF: A Plug-and-Play Framework for Enhanced Multi-object Multi-part Scene Parsing.- Progressive Pretext Task Learning for Human Trajectory Prediction.- Hyperion – A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM.- Isomorphic Pruning for Vision Models.- Attention Prompting on Image for Large Vision-Language Models.- Learning Cross-hand Policies of High-DOF Reaching and Grasping.- Reprojection Errors as Prompts for Efficient Scene Coordinate Regression.- Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning.- Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment.- REVISION: Rendering Tools Enable Spatial Fidelity in Vision-Language Models.- DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing.- VideoClusterNet: Self-Supervised and Adaptive Face Clustering for Videos.- Unveiling Privacy Risks in Stochastic Neural Networks Training: Effective Image Reconstruction from Gradients.- Controlling the World by Sleight of Hand.- Hiding Imperceptible Noise in Curvature-Aware Patches for 3D Point Cloud Attack.- Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection.- Cross-Domain Learning for Video Anomaly Detection with Limited Supervision.