LayerTracer：通过扩散Transformer实现与认知对齐的分层SVG合成

LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer

February 3, 2025

作者: Yiren Song, Danze Chen, Mike Zheng Shou

cs.AI

摘要

由于现有方法倾向于生成过于简化的单层输出或由优化引起的形状冗余，生成与认知对齐的分层SVG仍然具有挑战性。我们提出LayerTracer，这是一个基于扩散Transformer的框架，通过学习设计师的分层SVG创建过程，从一个新颖的顺序设计操作数据集中弥合了这一差距。我们的方法分为两个阶段：首先，一个文本条件的DiT生成多阶段栅格化建模蓝图，模拟人类设计工作流程。其次，通过逐层矢量化和路径去重，生成干净、可编辑的SVG。对于图像矢量化，我们引入了一种条件扩散机制，将参考图像编码为潜在标记，引导分层重建同时保持结构完整性。大量实验证明，LayerTracer在生成质量和可编辑性方面优于基于优化和神经网络的基线方法，有效地将AI生成的矢量与专业设计认知对齐。

English

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.