# SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis

arXiv: https://arxiv.org/abs/2406.09794 · HTML: https://mlsanity.com/paper/2406.09794/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 14 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Builds on (most cited first, 6 of 6)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Towards Layer-wise Image Vectorization](https://mlsanity.com/paper/2206.04655/) (2022)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)

## Built on by (most cited first, 19 of 19)

- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models](https://mlsanity.com/paper/2510.11341/) (2025)
- [Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedback](https://mlsanity.com/paper/2604.20730/) (2026)
- [VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation](https://mlsanity.com/paper/2605.01517/) (2026)
- [Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration](https://mlsanity.com/paper/2603.29590/) (2026)
- [SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation](https://mlsanity.com/paper/2412.10437/) (2024)
- [OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens](https://mlsanity.com/paper/2603.02138/) (2026)
- [AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling](https://mlsanity.com/paper/2604.10940/) (2026)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion](https://mlsanity.com/paper/2503.23752/) (2025)
- [Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding](https://mlsanity.com/paper/2510.12256/) (2025)
- [AnchorFlow: Learning Anchor Placement for Faithful and Editable SVG Reconstruction](https://mlsanity.com/paper/2605.19551/) (2026)
- [DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable](https://mlsanity.com/paper/2608.00548/) (2026)
- [A Scalable Vector Graphics Latent Space](https://mlsanity.com/paper/2608.21893/) (2026)
- [ProxyImg: Towards Highly-Controllable Image Representation via Hierarchical Disentangled Proxy Embedding](https://mlsanity.com/paper/2602.01881/) (2026)
- [CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation](https://mlsanity.com/paper/2608.20803/) (2026)
- [VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphics](https://mlsanity.com/paper/2609.13294/) (2026)

## Abstract (arXiv)

SVG (Scalable Vector Graphics) is a widely used graphics format that possesses excellent scalability and editability. Image vectorization, which aims to convert raster images to SVGs, is an important yet challenging problem in computer vision and graphics. Existing image vectorization methods either suffer from low reconstruction accuracy for complex images or require long computation time. To address this issue, we propose SuperSVG, a superpixel-based vectorization model that achieves fast and high-precision image vectorization. Specifically, we decompose the input image into superpixels to help the model focus on areas with similar colors and textures. Then, we propose a two-stage self-training framework, where a coarse-stage model is employed to reconstruct the main structure and a refinement-stage model is used for enriching the details. Moreover, we propose a novel dynamic path warping loss to help the refinement-stage model to inherit knowledge from the coarse-stage model. Extensive qualitative and quantitative experiments demonstrate the superior performance of our method in terms of reconstruction accuracy and inference time compared to state-of-the-art approaches. The code is available in urlhttps://github.com/sjtuplayer/SuperSVG.