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

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.

Visible and Clear: Finding Tiny Objects in Difference Map.- Rethinking Image Super Resolution from Training Data Perspectives.- BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering.- Efficient Inference of Vision Instruction-Following Models with Elastic Cache.- FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior.- Learning to Robustly Reconstruct Dynamic Scenes from Low-light Spike Streams.- MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection.- WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models.- Interactive 3D Object Detection with Prompts.- How Video Meetings Change Your Expression.- GRACE: Graph-Based Contextual Debiasing for Fair Visual Question Answering.- Neural Volumetric World Models for Autonomous Driving.- IVTP: Instruction-guided Visual Token Pruning for Large Vision-Language Models.- RegionDrag: Fast Region-Based Image Editing with Diffusion Models.- On the Error Analysis of 3D Gaussian Splatting and an Optimal Projection Strategy.- Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding.- Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration.- GRA: Detecting Oriented Objects through Group-wise Rotating and Attention.- A Simple Knowledge Distillation Framework for Generalizable Vision-Language Models.- Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer.- CSOT: Cross-Scan Object Transfer for Semi-Supervised LiDAR Object Detection.- Learning from the Web: Language Drives Weakly-Supervised Incremental Learning for Semantic Segmentation.- ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.- Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation.- Invertible Neural Warp for NeRF.- Enhancing Vectorized Map Perception with Historical Rasterized Maps.- Efficient and Versatile Robust Fine-Tuning of Zero-shot Models.