Description
Book SynopsisBridging 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.
