End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks (2020-11-11T00:00:00.000000Z)

TL;DR

The proposed Sketch-And-Paint GAN (SAPGAN), the first model which generates Chinese landscape paintings from end to end, without conditional input, lays a groundwork for truly machine-original art generation.

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.

Authors

Alice Xue

1 papers

TL;DR

Abstract

Authors

References32 items

Generative Adversarial Networks

Analyzing and Improving the Image Quality of StyleGAN

ChinaStyle: A Mask-Aware Generative Adversarial Network for Chinese Traditional Image Translation

Generating Chinese Classical Landscape Paintings Based on Cycle-Consistent Adversarial Networks

An Interactive and Generative Approach for Chinese Shanshui Painting Document

Predicting Future Frames Using Retrospective Cycle GAN

HoloGAN: Unsupervised Learning of 3D Representations From Natural Images

Semantic Image Synthesis With Spatially-Adaptive Normalization

A Style-Based Generator Architecture for Generative Adversarial Networks

Neural Abstract Style Transfer for Chinese Traditional Painting

ChipGAN: A Generative Adversarial Network for Chinese Ink Wash Painting Style Transfer

The relativistic discriminator: a key element missing from standard GAN

An Introduction to Image Synthesis with Generative Adversarial Nets

Transform a Simple Sketch to a Chinese Painting by a Multiscale Deep Neural Network

PacGAN: The Power of Two Samples in Generative Adversarial Networks

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

Toward Multimodal Image-to-Image Translation

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Skeleton-Aided Articulated Motion Generation

Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis

CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms

Learning to Generate Long-term Future via Hierarchical Prediction

Towards Diverse and Natural Image Descriptions via a Conditional GAN

ArtGAN: Artwork synthesis with conditional categorical GANs

Image-to-Image Translation with Conditional Adversarial Networks

LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation

Generative Image Modeling Using Style and Structure Adversarial Networks

A Neural Algorithm of Artistic Style

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Holistically-Nested Edge Detection

Conditional Generative Adversarial Nets

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names