Image vectorization using a sparse patch layout

Mesh-based image vectorization techniques have been studied for a long time, mostly owing to their compactness and flexibility in capturing image features. However, existing methods often lead to relatively dense meshes, especially when applied to images with high-frequency details or textures. We present a novel method that automatically vectorizes an image into a sparse collection of Coons patches whose size adapts to image features. To balance the number of patches and the accuracy of feature alignment, we generate the layout based on a harmonic cross field constrained by image features. We support T-junctions, which keeps the number of patches low and ensures local adaptation to feature density, naturally complemented by varying mesh-color resolution over the patches. Our experimental results demonstrate the utility, accuracy, and sparsity of our method. • We adopt Coons patches as the primary vector representation. • We utilize directional fields to guide the patch layout extraction and feature alignment. • Our method supports T-junctions in the patch layout, thus ensuring high sparsity. • Our algorithm can automatically vectorize and compress any raster image.