# Faster Unsupervised Semantic Inpainting: A GAN Based Approach

arXiv: https://arxiv.org/abs/1908.04968 · HTML: https://mlsanity.com/paper/1908.04968/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 3 of 3)

- [Regularising Inverse Problems with Generative Machine Learning Models](https://mlsanity.com/paper/2107.11191/) (2021)
- [Dynamic Object Removal for Effective Slam](https://mlsanity.com/paper/2303.10923/) (2023)
- [Masked Face Inpainting Through Residual Attention UNet](https://mlsanity.com/paper/2209.08850/) (2022)

## Abstract (arXiv)

In this paper, we propose to improve the inference speed and visual quality of contemporary baseline of Generative Adversarial Networks (GAN) based unsupervised semantic inpainting. This is made possible with better initialization of the core iterative optimization involved in the framework. To our best knowledge, this is also the first attempt of GAN based video inpainting with consideration to temporal cues. On single image inpainting, we achieve about 4.5-5× speedup and 80× on videos compared to baseline. Simultaneously, our method has better spatial and temporal reconstruction qualities as found on three image and one video dataset.