SuperSVG: Superpixel-based Scalable Vector Graphics Synthesis
Teng Hu, Ran Yi, Baihong Qian, Jiangning Zhang, Paul L. Rosin, Yu-Kun, Lai

TL;DR
SuperSVG introduces a superpixel-based, two-stage self-training method with a novel loss function for fast, high-precision SVG vectorization, outperforming existing techniques in accuracy and speed.
Contribution
It presents a new superpixel-based vectorization model with a two-stage framework and a dynamic path warping loss for improved SVG reconstruction.
Findings
Achieves superior reconstruction accuracy over state-of-the-art methods.
Provides faster inference times for complex images.
Demonstrates effectiveness through extensive experiments.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Computer Graphics and Visualization Techniques · Medical Image Segmentation Techniques
MethodsFocus
