Full Description
The multi-volume set LNCS 15623 until LNCS 15646 constitutes the proceedings of the workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024, which took place in Milan, Italy, during September 29-October 4, 2024.
These LNCS volumes contain 574 accepted papers from 53 of the 73 workshops. The list of workshops and distribution of the workshop papers in the LNCS volumes can be found in the preface that is freely accessible online.
Contents
Bridging Text and Image for Artist Style Transfer via Contrastive Learning.- Magic-Me: Identity-Specific Video Customized Diffusion.- Alfie: Democratising RGBA Image Generation With No $$$.- ComiCap: A VLM pipeline for dense captioning of Comic Panels.- Making Images from Images: Tightly Constrained Parallel Denoising.- ArCSEM: Artistic Colorization of SEM Images via Gaussian Splatting.- DreamWalk: Style Space Exploration using Diffusion Guidance.- An Art-centric perspective on AI-based content moderation of nudity.- Evaluation of Illustration Generators with Domain-Specific Representations.- Unlocking Comics: The AI4VA Dataset for Visual Understanding.- Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation.- Art Forgery Detection using Kolmogorov Arnold and Convolutional Neural Networks.- Sketch & Paint: Stroke-by-Stroke Evolution of Visual Artworks.- Storytelling Video Generation with Retrieval Augmentation and Character Consistency.- MACGaussian: Robust 3D Gaussian Splatting from sparse input views using high-precision Measurement-Arm-Camera (MAC) capture.- xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations.- VQA-Driven Facet-Level Texture Segmentation in 3D Surfaces.- Khattat: Enhancing Readability and Concept Representation of Semantic Typography.- Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning.
