Saved in:
Bibliographic Details
Main Authors: Lin, Xingyue, Peng, Shuai, Xie, Xiangyu, Zhu, Jianhua, Zhou, Yuxuan, Gao, Liangcai
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20034
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917332489601024
author Lin, Xingyue
Peng, Shuai
Xie, Xiangyu
Zhu, Jianhua
Zhou, Yuxuan
Gao, Liangcai
author_facet Lin, Xingyue
Peng, Shuai
Xie, Xiangyu
Zhu, Jianhua
Zhou, Yuxuan
Gao, Liangcai
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20034
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
Lin, Xingyue
Peng, Shuai
Xie, Xiangyu
Zhu, Jianhua
Zhou, Yuxuan
Gao, Liangcai
Computer Vision and Pattern Recognition
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.
title Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20034