In the first case, the non-standard representation prevents benefiting from latest network architectures for neural representations; while, in the latter case, therasterized representation, when encoded vianetworks, results inlossof data fidelity, as font-specific discontinuities like edges and corners are difficult torepresent using neural networks.

Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions. However, despite the success of deep learning-based models applied to rasterized images, the problem of vector graphics representation learning and generation remains largely unexplored. In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation.

Despite recent success of rasterized image generation and content creation, little effort has been directed towards generation of vector graphics. Y et, vector images, often in the form of Scalable V ector Graphics [20] (SVG), have become a standard in digital graphics, publication-ready image assets, and web-animations. The main advantage over their rasterized counterpart is their scaling ability, making the same image file suitable for both tiny web-icons or billboard-scale graphics.

Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions. However, despite the success of deep learning-based models applied to rasterized images, the problem of vector graphics representation learning and generation remains largely unexplored. In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. The network directly predicts a set of shapes in a non-autoregressive fashion. We introduce the task of complex SVG icons generation by releasing a new large-scale dataset along with an open-source library for SVG manipulation. We demonstrate that our network learns to accurately reconstruct diverse vector graphics, and can serve as a powerful animation tool by performing interpolations and other latent space operations.

This is the official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Please refer to section below for Citation details. Create a new conda environment (Python 3.7): Please refer to cairosvg's documentation for additional requirements of CairoSVG. If this is not working for you, download the dataset manually from Google Drive, place the files in the dataset folder, and unzip (this may take a few minutes). NOTE: The icons_tensor/ folder contains the 100k icons in pre-augmented PyTorch tensor format, which enables to easily reproduce our work.