A library for deep learning with SVG data, including export functionality to differentiable PyTorch tensors. The SVG-Icons8 dataset. A Graphical user interface showing a demo of DeepSVG for vector graphics animation.

Jul 22, 2020 · In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes from the low-level commands that encode the shape itself.

In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes from the low-level commands that encode the shape itself. The network directly predicts a set of shapes in a non-autoregressive fashion.

In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes from the low-level commands that encode the shape itself.

DeepSVG has been developed along with a library for deep learning with SVG data. The main features are: Parsing of SVG files. Conversion of basic shapes and commands to the subset m / l / c / z.

Jul 22, 2020 · In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes...

Instead of handling the SVG language as a standard language, the paper proposes a thoughtful way of embedding SVG draw-commands, converting tokens into higher dimensional representation through trainable weights.

[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data. ...

Sep 28, 2020 · In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes from the low-level commands that encode the shape itself. The network directly predicts a set of shapes in a non-autoregressive fashion.

In this work, we propose a novel hierarchical generative network, called DeepSVG, for complex SVG icons generation and interpolation. Our architecture effectively disentangles high-level shapes from the low-level commands that encode the shape itself.