# Image Vectorization: a Review

arXiv: https://arxiv.org/abs/2306.06441 · HTML: https://mlsanity.com/paper/2306.06441/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation](https://mlsanity.com/paper/2007.11301/) (2020)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models](https://mlsanity.com/paper/2211.11319/) (2022)
- [A Learned Representation for Scalable Vector Graphics](https://mlsanity.com/paper/1904.02632/) (2019)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation](https://mlsanity.com/paper/2202.12362/) (2022)
- [Deep Vectorization of Technical Drawings](https://mlsanity.com/paper/2003.05471/) (2020)
- [ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis](https://mlsanity.com/paper/2106.04912/) (2021)
- [Inverse Diffusion Curves using Shape Optimization](https://mlsanity.com/paper/1610.02769/) (2016)
- [Effective Clipart Image Vectorization Through Direct Optimization of Bezigons](https://mlsanity.com/paper/1602.01913/) (2016)
- [Conditional Vector Graphics Generation for Music Cover Images](https://mlsanity.com/paper/2205.07301/) (2022)
- [Neural Style Transfer for Vector Graphics](https://mlsanity.com/paper/2303.03405/) (2023)

## Built on by (most cited first, 7 of 7)

- [An Adaptive Screen-Space Meshing Approach for Normal Integration](https://mlsanity.com/paper/2409.16907/) (2024)
- [Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review](https://mlsanity.com/paper/2503.04983/) (2025)
- [AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction](https://mlsanity.com/paper/2605.19551/) (2026)
- [TGGLinesPlus: A robust topological graph-guided computer vision algorithm for line detection from images](https://mlsanity.com/paper/2403.18038/) (2024)
- [A Formalization of Image Vectorization by Region Merging](https://mlsanity.com/paper/2409.15940/) (2024)
- [An Active Contour Model for Silhouette Vectorization using B'ezier Curves](https://mlsanity.com/paper/2505.05132/) (2025)
- [MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems](https://mlsanity.com/paper/2508.21307/) (2025)

## Abstract (arXiv)

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.