Teaching GANs to sketch in vector format

V, Varshaneya and S, Balasubramanian and Balasubramanian, Vineeth N (2021) Teaching GANs to sketch in vector format. In: 12th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2021, 20 December 2021 through 22 December 2021, Virtual, Online.

[img] Text
ACM_International.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB)


Sketching is a fundamental human cognitive ability. Deep Neural Networks (DNNs) have achieved the state-of-the-art performance in recognition tasks like image recognition, speech recognition etc. but have not made significant progress in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture called SkeGAN and a hybrid VAE-GAN architecture called VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN draws sketches by coupling the efficient representation of data by VAE with the powerful generating capabilities of GAN. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches with minimal scribble effect and is comparable to a recent work titled Sketch-RNN. © 2021 ACM.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth Nhttps://orcid.org/0000-0003-2656-0375
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: GANs; Policy gradients; Sketch generation; Vector art
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 03 Oct 2022 15:14
Last Modified: 03 Oct 2022 15:14
URI: http://raiith.iith.ac.in/id/eprint/10786
Publisher URL: http://doi.org/10.1145/3490035.3490258
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 10786 Statistics for this ePrint Item