Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization

TL;DR

COVec is an illumination-aware vectorization framework that decomposes images into layers inspired by light-shade contrast, enabling more accurate and editable vector representations of complex real-world images.

Contribution

It introduces the first intrinsic image decomposition in the vector domain, enhancing vectorization quality with a novel illumination-aware approach.

Findings

Achieves higher visual fidelity than existing methods.

Significantly improves editability of vectorized images.

Demonstrates effectiveness across various datasets.

Abstract

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.