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

arXiv: https://arxiv.org/abs/2011.05552 · HTML: https://mlsanity.com/paper/2011.05552/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2020.

## Built on by (most cited first, 18 of 18)

- [The ArtBench Dataset: Benchmarking Generative Models with Artworks](https://mlsanity.com/paper/2206.11404/) (2022)
- [Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks](https://mlsanity.com/paper/2103.05422/) (2021)
- [QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation](https://mlsanity.com/paper/2507.04599/) (2025)
- [CCLAP: Controllable Chinese Landscape Painting Generation via Latent Diffusion Model](https://mlsanity.com/paper/2304.04156/) (2023)
- [Learning to Generate Poetic Chinese Landscape Painting with Calligraphy](https://mlsanity.com/paper/2305.04719/) (2023)
- [SCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer](https://mlsanity.com/paper/2503.04119/) (2025)
- [Computational Approaches for Traditional Chinese Painting: From the "Six Principles of Painting" Perspective](https://mlsanity.com/paper/2307.14227/) (2023)
- [Controllable Multi-domain Semantic Artwork Synthesis](https://mlsanity.com/paper/2308.10111/) (2023)
- [SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfer](https://mlsanity.com/paper/2404.15743/) (2024)
- [Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach](https://mlsanity.com/paper/2110.09170/) (2021)
- [Artistic Intelligence: A Diffusion-Based Framework for High-Fidelity Landscape Painting Synthesis](https://mlsanity.com/paper/2407.17229/) (2024)
- [Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks](https://mlsanity.com/paper/2410.19307/) (2024)
- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)
- [The Work of Art in an Age of Mechanical Generation](https://mlsanity.com/paper/2101.11587/) (2021)
- [Scene Depth Estimation from Traditional Oriental Landscape Paintings](https://mlsanity.com/paper/2403.03408/) (2024)
- [DLP-GAN: learning to draw modern Chinese landscape photos with generative adversarial network](https://mlsanity.com/paper/2403.03456/) (2024)
- [ConCLVD: Controllable Chinese Landscape Video Generation via Diffusion Model](https://mlsanity.com/paper/2404.12903/) (2024)
- [Neural-Polyptych: Content Controllable Painting Recreation for Diverse Genres](https://mlsanity.com/paper/2409.19690/) (2024)

## Abstract (arXiv)

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.