# DeepGIN: Deep Generative Inpainting Network for Extreme Image Inpainting

arXiv: https://arxiv.org/abs/2008.07173 · HTML: https://mlsanity.com/paper/2008.07173/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Aug 2020.

## Built on by (most cited first, 11 of 11)

- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation](https://mlsanity.com/paper/2209.05980/) (2022)
- [Markpainting: Adversarial Machine Learning meets Inpainting](https://mlsanity.com/paper/2106.00660/) (2021)
- [Intelligent Painter: Picture Composition With Resampling Diffusion Model](https://mlsanity.com/paper/2210.17106/) (2022)
- [StyleGAN-induced data-driven regularization for inverse problems](https://mlsanity.com/paper/2110.03814/) (2021)
- [See360: Novel Panoramic View Interpolation](https://mlsanity.com/paper/2401.03431/) (2024)
- [AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal](https://mlsanity.com/paper/2305.07857/) (2023)
- [A Highlight Removal Method for Capsule Endoscopy Images](https://mlsanity.com/paper/2402.07083/) (2024)
- [Task-Decoupled Image Inpainting Framework for Class-specific Object Remover](https://mlsanity.com/paper/2410.02894/) (2024)
- [MGAN-CRCM: A Novel Multiple Generative Adversarial Network and Coarse-Refinement Based Cognizant Method for Image Inpainting](https://mlsanity.com/paper/2412.19000/) (2024)

## Abstract (arXiv)

The degree of difficulty in image inpainting depends on the types and sizes of the missing parts. Existing image inpainting approaches usually encounter difficulties in completing the missing parts in the wild with pleasing visual and contextual results as they are trained for either dealing with one specific type of missing patterns (mask) or unilaterally assuming the shapes and/or sizes of the masked areas. We propose a deep generative inpainting network, named DeepGIN, to handle various types of masked images. We design a Spatial Pyramid Dilation (SPD) ResNet block to enable the use of distant features for reconstruction. We also employ Multi-Scale Self-Attention (MSSA) mechanism and Back Projection (BP) technique to enhance our inpainting results. Our DeepGIN outperforms the state-of-the-art approaches generally, including two publicly available datasets (FFHQ and Oxford Buildings), both quantitatively and qualitatively. We also demonstrate that our model is capable of completing masked images in the wild.