提出光照感知的矢量化方法，让图像转矢量更保真、易编辑。
Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
- 通过分解光照、阴影和颜色层，统一在矢量空间中处理。
- 在多个数据集上视觉保真度更高，编辑性显著优于现有方法。
- 适合需要高质量矢量图的设计师与图形编辑场景。
图像矢量化旨在将位图图像转换为可编辑、可缩放的矢量表示，同时保持视觉保真度。现有矢量化方法在处理复杂真实世界图像时表现不佳，常导致形状碎片化，牺牲语义简洁性。本文提出COVec，一种受明暗对比（Clair-Obscur）原理启发的光照感知矢量化框架。COVec首次在矢量域引入内在图像分解，将图像统一表示为反射率、阴影和光照三层。通过语义引导初始化与两阶段可微渲染优化，精细重构各层。在多个数据集上的实验表明，相比现有方法，COVec实现了更高的视觉保真度和显著提升的可编辑性。代码将于 https://github.com/decade-de/COVec 公开。
原文摘要 · Abstract (English)
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. The code will be released at https://github.com/decade-de/COVec.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。