Learnable Pixel Clustering Via Structure and Semantic Dual Constraints For Unsupervised Image Segmentation

We propose a novel algorithm converting quantized raster color images to resolution-independent scalable vector graphics (SVG). Starting from the discontinuity set of the input image, the algorithm connects the pieces of curves separating two constant regions to reconstruct the apparent contours of objects and interpret T-junctions and saddle points. This structure is depixelized by curve affine shortening, which requires maintaining the topology of the discontinuity set during filtering. The resulting Hierarchical Curve-based Vectorization (HCV) algorithm compares favourably to several state-of-art vectorization algorithms and software for color-quantized photos and pixel art