ShapeAR：通过自回归扩散生成可编辑形状层
ShapeAR: Generating Editable Shape Layers via Autoregressive Diffusion
把光栅图像分解为可编辑的 RGBA 矢量形状层，并用自回归流匹配扩散在潜空间中逐步生成，为图像矢量化与分层编辑提供了一条不依赖边界追踪的新路径；其几何感知评测指标也可复用于形状生成质量评估。
原文依据 generates non-overlapping RGBA shape layers directly in latent space via flow-matching diffusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 ShapeAR，一种新颖的自回归潜空间扩散框架，可将光栅图像分解为可编辑的、类似艺术家创作的矢量形状层。与依赖边界追踪或联合路径优化的传统光栅转 SVG 方法不同，ShapeAR 通过流匹配扩散直接在潜空间中生成互不重叠的 RGBA 形状层。为将生成扩展到包含大量形状的复杂场景，我们将该过程构造为自回归形式，每一步同时以输入图像（全局上下文）和已生成层的部分组合（局部上下文）为条件。此外，我们提出了几何感知的评测指标，用于量化所生成形状的美学与结构质量。
英文原文摘要 719 字符
We present ShapeAR, a novel autoregressive latent diffusion framework that decomposes raster images into editable, artist-like vector shape layers. Unlike conventional raster-to-SVG methods that rely on boundary tracing or joint path optimisation, ShapeAR generates non-overlapping RGBA shape layers directly in latent space via flow-matching diffusion. To scale generation to complex scenes with many shapes, we formulate the process auto-regressively, conditioning each step on both the input image (global context) and partial composition of previously generated layers (local context). In addition, we propose geometry-aware evaluation metrics that quantify aesthetic and structural quality of the generated shapes.