Layered Image Vectorization via Semantic Simplification

Zhenyu Wang, Jianxi Huang , Zhida Sun, Daniel Cohen-Or, Min Lu

This work presents a novel progressive image vectorization technique aimed at generating layered vectors that represent the original image from coarse to fine detail levels. Our approach introduces semantic simplification, which combines Score Distillation Sampling and semantic segmentation to iteratively simplify the input image. Subsequently, our method optimizes the vector layers for each of the progressively simplified images. Our method provides robust optimization, which avoids local minima and enables adjustable detail levels in the final output. The layered, compact vector representation enhances usability for further editing and modification.

If you find this useful for your research, please cite the following:

@article{Wang2024Layered,
  title={Layered Image Vectorization via Semantic Simplification},
  author={Zhenyu Wang, Jianxi Huang, Zhida Sun, Daniel Cohen-Or and Min Lu},
  journal={arXiv preprint },
  year={2024}
}