# Generator Pyramid for High-Resolution Image Inpainting

arXiv: https://arxiv.org/abs/2012.02381 · HTML: https://mlsanity.com/paper/2012.02381/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 2 of 2)

- [ExSinGAN: Learning an Explainable Generative Model from a Single Image](https://mlsanity.com/paper/2105.07350/) (2021)
- [Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter](https://mlsanity.com/paper/2510.13419/) (2025)

## Abstract (arXiv)

Inpainting high-resolution images with large holes challenges existing deep learning based image inpainting methods. We present a novel framework -- PyramidFill for high-resolution image inpainting task, which explicitly disentangles content completion and texture synthesis. PyramidFill attempts to complete the content of unknown regions in a lower-resolution image, and synthesis the textures of unknown regions in a higher-resolution image, progressively. Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image. Since completing contents and synthesising textures demand different abilities from generators, we customize different architectures for the content GAN and texture GAN. Experiments on multiple datasets including CelebA-HQ, Places2 and a new natural scenery dataset (NSHQ) with different resolutions demonstrate that PyramidFill generates higher-quality inpainting results than the state-of-the-art methods. To better assess high-resolution image inpainting methods, we will release NSHQ, high-quality natural scenery images with high-resolution 1920×1080.