End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks release_iggegdkrufhs7pfw6l2vtzxpzq

by Alice Xue

Released as a article .

2020  

Abstract

Current GAN-based art generation methods produce unoriginal artwork due to their dependence on conditional input. Here, we propose Sketch-And-Paint GAN (SAPGAN), the first model which generates Chinese landscape paintings from end to end, without conditional input. SAPGAN is composed of two GANs: SketchGAN for generation of edge maps, and PaintGAN for subsequent edge-to-painting translation. Our model is trained on a new dataset of traditional Chinese landscape paintings never before used for generative research. A 242-person Visual Turing Test study reveals that SAPGAN paintings are mistaken as human artwork with 55% frequency, significantly outperforming paintings from baseline GANs. Our work lays a groundwork for truly machine-original art generation.
In text/plain format

Archived Files and Locations

application/pdf  6.5 MB
file_3vpmbx2cnzgbteo7ssw4mhtcvy
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Archived
Type  article
Stage   submitted
Date   2020-11-11
Version   v1
Language   en ?
arXiv  2011.05552v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 95ded9a1-4f04-476d-acf3-ec4c9c9aa742
API URL: JSON