CraGL: Computational Reality, Creativity and Graphics Lab

Image vectorization and editing via linear gradient layer decomposition

Zheng-Jun Du, Liang-Fu Kang, Jianchao Tan, Yotam Gingold, Kun Xu
ACM SIGGRAPH North America 2023 (Journal Papers). Also in ACM Transactions on Graphics (TOG) 42(4).

Paper

Presentation

Supplementary Material

Code

A soda can graphic, the graphic segmented into regions with similar colors, the soda can decomposed into coherent translucent layers, the soda can with a different base color, the soda can with the letters SIG and the SIGGRAPH logo composited underneath a highlight. Given the input image (1st column) and a segmentation mask (2nd column), we can decompose the image into several linear gradient layers to be saved in vector graphics (3rd column). Then we can perform recoloring (4th column) or object remove-insert-replace edits using these linear gradient layers in illustrator software (5th column). Image designed by Altagracia Art on Shutterstock.com.

Abstract

A key advantage of vector graphics over raster graphics is their editability. For example, linear gradients define a spatially varying color fill with a few intuitive parameters, which are ubiquitously supported in standard vector graphics formats and libraries. By layering regions filled with linear gradients, complex appearances can be created. We propose an automatic method to convert a raster image into layered regions of linear gradients. Given an input raster image segmented into regions, our approach decomposes the resulting regions into opaque and semi-transparent linear gradient fills. Our approach is fully automatic (e.g., users do not identify a background as in previous approaches) and exhaustively considers all possible decompositions that satisfy perceptual cues. Experiments on a variety of images demonstrate that our method is robust and effective.

Fast Forward (20 seconds)

Download as:

BibTeX

(approximate) 

@article{Du:2023:IVE,
 author    = {Du, Zheng-Jun and Kang, Liang-Fu and Tan, Jianchao and Gingold, Yotam and Xu, Kun},
 title     = {Image vectorization and editing via linear gradient layer decomposition},
 journal   = {ACM Transactions on Graphics (TOG)},
 volume    = {42},
 number    = {4},
 year      = {2023},
 month     = aug,
 keywords  = {images, gradient, layers, vectorization, RGB, color space, recoloring, compositing}
}