# A Wasserstein GAN for Joint Learning of Inpainting and Spatial Optimisation

arXiv: https://arxiv.org/abs/2202.05623 · HTML: https://mlsanity.com/paper/2202.05623/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 11 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Coherent Semantic Attention for Image Inpainting](https://mlsanity.com/paper/1905.12384/) (2019)
- [Region Normalization for Image Inpainting](https://mlsanity.com/paper/1911.10375/) (2019)
- [Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction](https://mlsanity.com/paper/1812.10836/) (2018)
- [Learning Sparse Masks for Diffusion-based Image Inpainting](https://mlsanity.com/paper/2110.02636/) (2021)
- [A bi-level view of inpainting - based image compression](https://mlsanity.com/paper/1401.4112/) (2014)
- [Efficient Data Optimisation for Harmonic Inpainting with Finite Elements](https://mlsanity.com/paper/2105.01586/) (2021)
- [Image Inpainting Using Wasserstein Generative Adversarial Imputation Network](https://mlsanity.com/paper/2106.15341/) (2021)

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

- [Efficient Neural Generation of 4K Masks for Homogeneous Diffusion Inpainting](https://mlsanity.com/paper/2303.10096/) (2023)

## Abstract (arXiv)

Image inpainting is a restoration method that reconstructs missing image parts. However, a carefully selected mask of known pixels that yield a high quality inpainting can also act as a sparse image representation. This challenging spatial optimisation problem is essential for practical applications such as compression. So far, it has been almost exclusively adressed by model-based approaches. First attempts with neural networks seem promising, but are tailored towards specific inpainting operators or require postprocessing. To address this issue, we propose the first generative adversarial network (GAN) for spatial inpainting data optimisation. In contrast to previous approaches, it allows joint training of an inpainting generator and a corresponding mask optimisation network. With a Wasserstein distance, we ensure that our inpainting results accurately reflect the statistics of natural images. This yields significant improvements in visual quality and speed over conventional stochastic models. It also outperforms current spatial optimisation networks.