明暗对照：一种光照感知的真实世界图像矢量化方法
Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
将本征图像分解（albedo/shade/light）引入矢量域，用可微渲染做两阶段优化，为图像矢量化提供光照感知的表示，可复用于需要可编辑矢量表示或光照解耦的视觉任务。
原文依据 COVec is the first to introduce intrinsic image decomposition in the vector domain, separating an image into albedo, shade, and light layers in a unified vector representation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像矢量化旨在将栅格图像转换为可编辑、可缩放的矢量表示，同时保持视觉保真度。现有矢量化方法难以表示复杂的真实世界图像，往往产生碎片化的形状，牺牲了语义简洁性。本文提出COVec，一种受明暗对照（Clair-Obscur）光影对比原理启发的光照感知矢量化框架。COVec首次在矢量域引入本征图像分解，将图像分离为反照率、阴影和光照层，并以统一的矢量表示呈现。语义引导的初始化和两阶段优化通过可微渲染对这些层进行细化。在各种数据集上的实验表明，与现有方法相比，COVec实现了更高的视觉保真度和显著提升的可编辑性。
英文原文摘要 868 字符
Image vectorization aims to convert raster images into editable, scalable vector representations while preserving visual fidelity. Existing vectorization methods struggle to represent complex real-world images, often producing fragmented shapes at the cost of semantic conciseness. In this paper, we propose COVec, an illumination-aware vectorization framework inspired by the Clair-Obscur principle of light-shade contrast. COVec is the first to introduce intrinsic image decomposition in the vector domain, separating an image into albedo, shade, and light layers in a unified vector representation. A semantic-guided initialization and two-stage optimization refine these layers with differentiable rendering. Experiments on various datasets demonstrate that COVec achieves higher visual fidelity and significantly improved editability compared to existing methods.