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

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.

GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection.- MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks.- Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?.- PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation.- A Comparative Study of Image Restoration Networks for General Backbone Network Design.- Learned Image Enhancement via Color Naming.- Synthesizing Time-varying BRDFs via Latent Space.- HoloADMM: High-Quality Holographic Complex Field Recovery.- Fundamental Matrix Estimation Using Relative Depths.- Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion.- MTaDCS: Moving Trace and Feature Density-based Confidence Sample Selection under Label Noise.- Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis.- GroundUp: Rapid Sketch-Based 3D City Massing.- Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing.- DataDream: Few-shot Guided Dataset Generation.- LPViT: Low-Power Semi-structured Pruning for Vision Transformers.- CipherDM: Secure Three-Party Inference for Diffusion Model Sampling.- Weighted Ensemble Models Are Strong Continual Learners.- GGRt: Towards Generalizable 3D Gaussians without Pose Priors in Real-Time.- A Unified Image Compression Method for Human Perception and Multiple Vision Tasks.- UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation.- Audio-visual Generalized Zero-shot Learning the Easy Way.- PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition.- Learning Equilibrium Transformation for Gamut Expansion and Color Restoration.- Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition.- Physics-informed Knowledge Transfer for Underwater Monocular Depth Estimation.