DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

By Alexandre Carlier, Martin Danelljan, Alexandre Alahi, Radu Timofte. 2020

221 citations recorded by the source corpus.

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 this https URL.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Control and Systems Engineering, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

1. Simon Lacoste-Julien
2. Rundi Wu
3. Cees G. M. Snoek
4. Niloy J. Mitra
5. Richard S. Zemel
6. Alexander Wang
7. Yue Wang
8. Yicheng Liu

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Li Fei-Fei
6. Bernt Schiele
7. Trevor Darrell
8. Jitendra Malik

In Control and Systems Engineering

1. Simon Lacoste-Julien
2. Cees G. M. Snoek
3. Niloy J. Mitra
4. Richard S. Zemel
5. Alexander Wang
6. Yue Wang
7. Yicheng Liu
8. Mengye Ren

In Generative Models

1. Simon Lacoste-Julien
2. Rundi Wu
3. Cees G. M. Snoek
4. Niloy J. Mitra
5. Richard S. Zemel
6. Gertjan J. Burghouts
7. Alexander Wang
8. Yue Wang

Citations in the corpus

• Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation (2021, background): “Example applications include speaker diarization (Fujita et al., 2019), vector graphics generation (Carlier et al., 2020), object detection (Carion et al., 2020) and point cloud generation (Achlioptas et al., 2018).”
• DeepCAD: A Deep Generative Network for Computer-Aided Design Models (2021, methodology): “It takes as input learned constant embeddings while also attending to the latent vector z—similar input structure has been used in [9, 10].”
• SketchEmbedNet: Learning Novel Concepts by Imitating Drawings (2020, background): “It has also been demonstrated in human face images and vector graphics (Bojanowski et al., 2018; Shen et al., 2020; Carlier et al., 2020).”
• VectorMapNet: End-to-end Vectorized HD Map Learning (2022, methodology): “These methods typically treat geometric elements as a sequence, such as primitive parts of furniture (Li et al., 2017; Mo et al., 2019), states of sketch strokes (Ha & Eck, 2017), vertices of n -gon mesh (Nash et al., 2020), and parameters of SVG primitives (Carlier et al., 2020).”
• Im2Vec: Synthesizing Vector Graphics without Vector Supervision (2021, background): “SVG-VAE [24] and DeepSVG [5], the two leading generative algorithms for vector graphics, cast synthesis as a sequence prediction problem, where the graphic is a sequence of drawing instructions, mimicking how common formats actually represent vector art.”