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

FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation.- BugNIST - a Large Volumetric Dataset for Detection under Domain Shift.- SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis.- PoseAugment: Generative Human Pose Data Augmentation with Physical Plausibility for IMU-based Motion Capture.- PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation.- Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection.- A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks.- Improving Unsupervised Domain Adaptation: A Pseudo-Candidate Set Approach.- HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting.- DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM.- Surface-Centric Modeling for High-Fidelity Generalizable Neural Surface Reconstruction.- HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance.- Multiscale Graph Texture Network.- HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis.- Integer-Valued Training and Spike-driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection.- RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception.- Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation.- Group Testing for Accurate and Efficient Range-Based Near Neighbor Search for Plagiarism Detection.- CompGS: Smaller and Faster Gaussian Splatting with Vector Quantization.- SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection.- S-JEPA: A Joint Embedding Predictive Architecture for Skeletal Action Recognition.- -Brush: Controllable Large Image Synthesis with Diffusion Models in Infinite Dimensions.- SwapAnything: Enabling Arbitrary Object Swapping in Personalized Image Editing.- Interaction-centric Spatio-Temporal Context Reasoning for Multi-Person Video HOI Recognition.- Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing.- ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation.- Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos.