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

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.

ST-LLM: Large Language Models Are Effective Temporal Learners.- Exact Diffusion Inversion via Bidirectional Integration Approximation.- Textual Query-Driven Mask Transformer for Domain Generalized Segmentation.- EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head.- Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors.- Object-Centric Diffusion for Efficient Video Editing.- Single-Mask Inpainting for Voxel-based Neural Radiance Fields.- McGrids: Monte Carlo-Driven Adaptive Grids for Iso-Surface Extraction.- Freeview Sketching: View-Aware Fine-Grained Sketch-Based Image Retrieval.- Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts.- Diffusion for Natural Image Matting.- Agglomerative Token Clustering.- CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection.- Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning.- ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition.- NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition.- GIVT: Generative Infinite-Vocabulary Transformers.- Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment.- Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density.- Multi-Modal Video Dialog State Tracking in the Wild.- Factorized Diffusion: Perceptual Illusions by Noise Decomposition.- To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now.- Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions.- StereoGlue: Joint Feature Matching and Robust Estimation.- Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory.- Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction.- Robust Zero-Shot Crowd Counting and Localization with Adaptive Resolution SAM.