{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer","html":"","width":"100%","height":180,"duration":1533,"description":"\n 🤗 Upvotes: 7 | cs.CV\n\n Authors:\n Yiren Song, Danze Chen, Mike Zheng Shou\n\n Title:\n LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer\n\n Arxiv:\n http://arxiv.org/abs/2502.01105v1\n\n Abstract:\n Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplication produces clean, editable SVGs. For image vectorization, we introduce a conditional diffusion mechanism that encodes reference images into latent tokens, guiding hierarchical reconstruction while preserving structural integrity. Extensive experiments demonstrate LayerTracer's superior performance against optimization-based and neural baselines in both generation quality and editability, effectively aligning AI-generated vectors with professional design cognition.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}