AI RESEARCH
Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
arXiv CS.CV
•
ArXi:2511.20034v2 Announce Type: replace 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