LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

• URL: http://arxiv.org/abs/2502.01105v1
• Date: Mon, 03 Feb 2025 06:49:58 GMT
• Title: LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer
• Authors: Yiren Song, Danze Chen, Mike Zheng Shou,
• Abstract summary: LayerTracer is a diffusion transformer that bridges the gap by learning designers' layered creation processes from a novel dataset of sequential design operations. For image vectorization, we introduce a conditional diffusion mechanism that encodes reference images into latent tokens. Experiments demonstrate LayerTracer's superior performance against optimization-based and neural baselines in both generation quality and editability.
• Score: 17.881925697226656
• License:
• Abstract: 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.

Related papers

• NeuralSVG: An Implicit Representation for Text-to-Vector Generation [54.4153300455889]
  We propose NeuralSVG, an implicit neural representation for generating vector graphics from text prompts. To encourage a layered structure in the generated SVG, we introduce a dropout-based regularization technique. We demonstrate that NeuralSVG outperforms existing methods in generating structured and flexible SVG.
  arXiv  Detail & Related papers  (2025-01-07T18:50:06Z)
• SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation [31.76771064173087]
  We propose a novel text-guided vector graphics synthesis method to address limitations of existing methods. We introduce a Hierarchical Image VEctorization (HIVE) framework that operates at the semantic object level. We also present a Vectorized Particle-based Score Distillation (VPSD) approach to improve the diversity of output SVGs.
  arXiv  Detail & Related papers  (2024-11-26T19:13:38Z)
• Segmentation-guided Layer-wise Image Vectorization with Gradient Fills [6.037332707968933]
  We propose a segmentation-guided vectorization framework to convert images into concise vector graphics with gradient fills. With the guidance of an embedded gradient-aware segmentation, our approach progressively appends gradient-filled B'ezier paths to the output.
  arXiv  Detail & Related papers  (2024-08-28T12:08:25Z)
• Text-to-Vector Generation with Neural Path Representation [27.949704002538944]
  We propose a novel neural path representation that learns the path latent space from both sequence and image modalities. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure.
  arXiv  Detail & Related papers  (2024-05-16T17:59:22Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• StraIT: Non-autoregressive Generation with Stratified Image Transformer [63.158996766036736]
  Stratified Image Transformer(StraIT) is a pure non-autoregressive(NAR) generative model. Our experiments demonstrate that StraIT significantly improves NAR generation and out-performs existing DMs and AR methods.
  arXiv  Detail & Related papers  (2023-03-01T18:59:33Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)
• Towards Layer-wise Image Vectorization [57.26058135389497]
  We propose Layerwise Image Vectorization, namely LIVE, to convert images to SVGs and simultaneously maintain its image topology. Live generates compact forms with layer-wise structures that are semantically consistent with human perspective. Live initiates human editable SVGs for both designers and can be used in other applications.
  arXiv  Detail & Related papers  (2022-06-09T17:55:02Z)
• Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model [58.17021225930069]
  We explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) We propose a more efficient EAT model, and design task-related heads to deal with different tasks more flexibly. Our approach achieves state-of-the-art results on the ImageNet classification task compared with recent vision transformer works.
  arXiv  Detail & Related papers  (2021-05-31T16:20:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.