Image Vectorization via Gradient Reconstruction

Abstract
We present a fully automated technique that segments raster images into smooth shaded regions and reconstructs them using an optimal mix of solid fills, linear gradients, and radial gradients. Our method leverages a novel discontinuity-aware segmentation strategy and gradient reconstruction algorithm to accurately capture intricate shading details and produce compact Bézier curve representations. Extensive evaluations on both designer-created art and generative images demonstrate that our approach achieves high visual fidelity with minimal geometric complexity and fast processing times. This work offers a robust and versatile solution for converting detailed raster images into scalable vector graphics, addressing the evolving needs of modern design workflows.
Description

CCS Concepts: Computing methodologies → Image processing

        
@article{
10.1111:cgf.70055
, journal = {Computer Graphics Forum}, title = {{
Image Vectorization via Gradient Reconstruction
}}, author = {
Chakraborty, Souymodip
and
Batra, Vineet
and
Phogat, Ankit
and
Jain, Vishwas
and
Ranawat, Jaswant Singh
and
Dhingra, Sumit
and
Wampler, Kevin
and
Fisher, Matthew
and
Lukác, Michal
}, year = {
2025
}, publisher = {
The Eurographics Association and John Wiley & Sons Ltd.
}, ISSN = {
1467-8659
}, DOI = {
10.1111/cgf.70055
} }
Citation