Image Vectorization: a Review

TL;DR

This review analyzes machine learning methods for vectorizing raster images into minimal shape representations, highlighting current limitations and the need for human oversight due to accuracy and speed issues.

Contribution

The paper provides a comprehensive overview of existing ML-based vectorization methods and discusses their limitations, emphasizing the necessity of human control.

Findings

Existing methods are slow and often inaccurate in recreating original images.

No universal fast automatic vectorization approach currently exists.

Human intervention remains essential for quality and precision.

Abstract

Nowadays, there are 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 looks very promising. Instead of generating vector images directly, you 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, generated vector image is also required to contain the minimum number of shapes for rendering. In this paper, we focus specifically on machine learning-compatible vectorization methods. We are considering 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 work for 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.