Towards Layer-wise Image Vectorization

by   Xu Ma, et al.

Image rasterization is a mature technique in computer graphics, while image vectorization, the reverse path of rasterization, remains a major challenge. Recent advanced deep learning-based models achieve vectorization and semantic interpolation of vector graphs and demonstrate a better topology of generating new figures. However, deep models cannot be easily generalized to out-of-domain testing data. The generated SVGs also contain complex and redundant shapes that are not quite convenient for further editing. Specifically, the crucial layer-wise topology and fundamental semantics in images are still not well understood and thus not fully explored. In this work, we propose Layer-wise Image Vectorization, namely LIVE, to convert raster images to SVGs and simultaneously maintain its image topology. LIVE can generate compact SVG forms with layer-wise structures that are semantically consistent with human perspective. We progressively add new bezier paths and optimize these paths with the layer-wise framework, newly designed loss functions, and component-wise path initialization technique. Our experiments demonstrate that LIVE presents more plausible vectorized forms than prior works and can be generalized to new images. With the help of this newly learned topology, LIVE initiates human editable SVGs for both designers and other downstream applications. Codes are made available at


page 1

page 7

page 13

page 14

page 16

page 17

page 18

page 19


Text-Guided Vector Graphics Customization

Vector graphics are widely used in digital art and valued by designers f...

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces du...

The role of a layer in deep neural networks: a Gaussian Process perspective

A fundamental question in deep learning concerns the role played by indi...

FSDiffReg: Feature-wise and Score-wise Diffusion-guided Unsupervised Deformable Image Registration for Cardiac Images

Unsupervised deformable image registration is one of the challenging tas...

Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagation

This paper contributes to automating medical image segmentation by propo...

Image Vectorization: a Review

Nowadays, there are many diffusion and autoregressive models that show i...

HumanLiff: Layer-wise 3D Human Generation with Diffusion Model

3D human generation from 2D images has achieved remarkable progress thro...

Please sign up or login with your details

Forgot password? Click here to reset