Image vectorization: a review

Nowadays, there exist many diffusion and autoregressive models that show impressive results for generating images from text and other input domains. However, these methods are not intended for ultra-high-resolution image synthesis. Vector graphics are devoid of this disadvantage, so the generation of images in this format appears to be a very promising direction. Instead of generating vector images directly, one can first synthesize a raster image and then apply vectorization. Vectorization is the process of converting a raster image into a similar vector image using primitive shapes. Besides being similar, the generated vector image is also required to contain a minimal number of shapes for rendering. In this work, we focus specifically on machine learning-compatible vectorization methods. We consider Mang2Vec, Deep Vectorization of Technical Drawings, DiffVG, and LIVE models. We also provide a brief overview of existing online methods. We also recall other algorithmic methods, Im2Vec and ClipGEN models, but they do not participate in the comparison, since there is no open implementation of these methods or their official implementations do not work correctly. Our research shows that despite the ability to directly specify the number and type of shapes, existing machine learning methods take a very long time and do not accurately recreate the original image. We believe that there is no fast universal automatic approach and human control is required for every method.