Timezone: »
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. 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. 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. Our code is available at https://github.com/alexandre01/deepsvg.
Author Information
Alexandre Carlier (Litso AI | ETH Zurich)
Founder of Litso AI. Creator of DeepSVG. Previously ML at Amazon, CS from ETH Zurich.
Martin Danelljan (ETH Zurich)
Alexandre Alahi (EPFL)
Radu Timofte (ETH Zurich)
More from the Same Authors
-
2021 Spotlight: Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation »
Lei Ke · Xia Li · Martin Danelljan · Yu-Wing Tai · Chi-Keung Tang · Fisher Yu -
2021 : DriverGym: Democratising Reinforcement Learning for Autonomous Driving »
Parth Kothari · Christian Perone · Luca Bergamini · Alexandre Alahi · Peter Ondruska -
2021 : Towards Robust and Adaptable Motion Forecasting: A Causal Representation Perspective »
Yuejiang Liu · Alexandre Alahi -
2022 : A generic diffusion-based approach for 3D human pose prediction in the wild »
Saeed Saadatnejad · Ali Rasekh · Mohammadreza Mofayezi · Yasamin Medghalchi · Sara Rajabzadeh · Taylor Mordan · Alexandre Alahi -
2021 Poster: Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation »
Lei Ke · Xia Li · Martin Danelljan · Yu-Wing Tai · Chi-Keung Tang · Fisher Yu -
2021 Poster: TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? »
Yuejiang Liu · Parth Kothari · Bastien van Delft · Baptiste Bellot-Gurlet · Taylor Mordan · Alexandre Alahi -
2020 Poster: GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network »
Prune Truong · Martin Danelljan · Luc V Gool · Radu Timofte -
2017 Poster: Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations »
Eirikur Agustsson · Fabian Mentzer · Michael Tschannen · Lukas Cavigelli · Radu Timofte · Luca Benini · Luc V Gool