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

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.

GeoCalib: Learning Single-image Calibration with Geometric Optimization.- 3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation.- Semicalibrated Relative Pose from an Affine Correspondence and Monodepth.- Global Structure-from-Motion Revisited.- MobileNetV4: Universal Models for the Mobile Ecosystem.- Gravity-aligned Rotation Averaging with Circular Regression.- MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation.- Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments.- Quanta Video Restoration.- Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models.- CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model.- ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image.- POCA: Post-training Quantization with Temporal Alignment for Codec Avatars.- HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts.- Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras.- Unsupervised Dense Prediction using Differentiable Normalized Cuts.- Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training.- Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization.- AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion.- Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers.- EINet: Point Cloud Completion via Extrapolation and Interpolation.- Personalized Video Relighting With an At-Home Light Stage.- Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction.- A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks.- SPIRE: Semantic Prompt-Driven Image Restoration.- Free-ATM: Harnessing Free Attention Masks for Representation Learning on Diffusion-Generated Images.- HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution.