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

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.

COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation.- Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography.- SpatialFormer: Towards Generalizable Vision Transformers with Explicit Spatial Understanding.- OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving.- MyVLM: Personalizing VLMs for User-Specific Queries.- AMEGO: Active Memory from long EGOcentric videos.- Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment.- Collaborative Control for Geometry-Conditioned PBR Image Generation.- Co-synthesis of Histopathology Nuclei Image-Label Pairs using a Context-Conditioned Joint Diffusion Model.- One-stage Prompt-based Continual Learning.- SpaceJAM: a Lightweight and Regularization-free Method for Fast Joint Alignment of Images.- APL: Anchor-based Prompt Learning for One-stage Weakly Supervised Referring Expression Comprehension.- GenQ: Quantization in Low Data Regimes with Generative Synthetic Data.- MVDD: Multi-View Depth Diffusion Models.- Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data.- Risk-Aware Self-Consistent Imitation Learning for Trajectory Planning in Autonomous Driving.- Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation.- EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models.- DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators.- Harnessing Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation.- SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer.- Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks.- Large Motion Model for Unified Multi-Modal Motion Generation.- FisherRF: Active View Selection and Mapping with Radiance Fields using Fisher Information.- Occlusion Handling in 3D Human Pose Estimation with Perturbed Positional Encoding.- Gradient-based Out-of-Distribution Detection.- Event-based Mosaicing Bundle Adjustment.