# R-MNet: A Perceptual Adversarial Network for Image Inpainting

arXiv: https://arxiv.org/abs/2008.04621 · HTML: https://mlsanity.com/paper/2008.04621/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 12 of 12)

- [Depth-Aware Generative Adversarial Network for Talking Head Video Generation](https://mlsanity.com/paper/2203.06605/) (2022)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces](https://mlsanity.com/paper/2110.09425/) (2021)
- [Foreground-guided Facial Inpainting with Fidelity Preservation](https://mlsanity.com/paper/2105.03342/) (2021)
- [A Comprehensive Survey of Masked Faces: Recognition, Detection, and Unmasking](https://mlsanity.com/paper/2405.05900/) (2024)
- [V-LinkNet: Learning Contextual Inpainting Across Latent Space of Generative Adversarial Network](https://mlsanity.com/paper/2201.00323/) (2022)
- [Improve Deep Image Inpainting by Emphasizing the Complexity of Missing Regions](https://mlsanity.com/paper/2202.06266/) (2022)
- [Enhancing Gappy Speech Audio Signals with Generative Adversarial Networks](https://mlsanity.com/paper/2305.05780/) (2023)
- [AURA : Automatic Mask Generator using Randomized Input Sampling for Object Removal](https://mlsanity.com/paper/2305.07857/) (2023)
- [Spatial-and-Frequency-aware Restoration method for Images based on Diffusion Models](https://mlsanity.com/paper/2401.17629/) (2024)
- [FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image](https://mlsanity.com/paper/2406.07865/) (2024)
- [Task-Decoupled Image Inpainting Framework for Class-specific Object Remover](https://mlsanity.com/paper/2410.02894/) (2024)

## Abstract (arXiv)

Facial image inpainting is a problem that is widely studied, and in recent years the introduction of Generative Adversarial Networks, has led to improvements in the field. Unfortunately some issues persists, in particular when blending the missing pixels with the visible ones. We address the problem by proposing a Wasserstein GAN combined with a new reverse mask operator, namely Reverse Masking Network (R-MNet), a perceptual adversarial network for image inpainting. The reverse mask operator transfers the reverse masked image to the end of the encoder-decoder network leaving only valid pixels to be inpainted. Additionally, we propose a new loss function computed in feature space to target only valid pixels combined with adversarial training. These then capture data distributions and generate images similar to those in the training data with achieved realism (realistic and coherent) on the output images. We evaluate our method on publicly available dataset, and compare with state-of-the-art methods. We show that our method is able to generalize to high-resolution inpainting task, and further show more realistic outputs that are plausible to the human visual system when compared with the state-of-the-art methods.