# Continuation of Famous Art with AI: A Conditional Adversarial Network Inpainting Approach

arXiv: https://arxiv.org/abs/2110.09170 · HTML: https://mlsanity.com/paper/2110.09170/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 63 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Adversarial Feature Learning](https://mlsanity.com/paper/1605.09782/) (2016)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [Adversarially Learned Inference](https://mlsanity.com/paper/1606.00704/) (2016)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [ArtEmis: Affective Language for Visual Art](https://mlsanity.com/paper/2101.07396/) (2021)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [Patch-Based Image Inpainting with Generative Adversarial Networks](https://mlsanity.com/paper/1803.07422/) (2018)
- [Learning to Incorporate Structure Knowledge for Image Inpainting](https://mlsanity.com/paper/2002.04170/) (2020)
- [End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks](https://mlsanity.com/paper/2011.05552/) (2020)
- [ArtGAN: Artwork Synthesis with Conditional Categorical GANs](https://mlsanity.com/paper/1702.03410/) (2017)
- [End-to-End Conditional GAN-based Architectures for Image Colourisation](https://mlsanity.com/paper/1908.09873/) (2019)
- [Toward Quantifying Ambiguities in Artistic Images](https://mlsanity.com/paper/2008.09688/) (2020)
- [Adversarial nets with perceptual losses for text-to-image synthesis](https://mlsanity.com/paper/1708.09321/) (2017)

## Built on by (most cited first, 1 of 1)

- [Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey](https://mlsanity.com/paper/2412.01450/) (2024)

## Abstract (arXiv)

Much of the state-of-the-art in image synthesis inspired by real artwork are either entirely generative by filtered random noise or inspired by the transfer of style. This work explores the application of image inpainting to continue famous artworks and produce generative art with a Conditional GAN. During the training stage of the process, the borders of images are cropped, leaving only the centre. An inpainting GAN is then tasked with learning to reconstruct the original image from the centre crop by way of minimising both adversarial and absolute difference losses, which are analysed by both their Fr'echet Inception Distances and manual observations which are presented. Once the network is trained, images are then resized rather than cropped and presented as input to the generator. Following the learning process, the generator then creates new images by continuing from the edges of the original piece. Three experiments are performed with datasets of 4766 landscape paintings (impressionism and romanticism), 1167 Ukiyo-e works from the Japanese Edo period, and 4968 abstract artworks. Results show that geometry and texture (including canvas and paint) as well as scenery such as sky, clouds, water, land (including hills and mountains), grass, and flowers are implemented by the generator when extending real artworks. In the Ukiyo-e experiments, it was observed that features such as written text were generated even in cases where the original image did not have any, due to the presence of an unpainted border within the input image.