# MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network

arXiv: https://arxiv.org/abs/2010.01424 · HTML: https://mlsanity.com/paper/2010.01424/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes](https://mlsanity.com/paper/2103.14211/) (2021)
- [FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces](https://mlsanity.com/paper/2110.09425/) (2021)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [Mask-Guided Discovery of Semantic Manifolds in Generative Models](https://mlsanity.com/paper/2105.07273/) (2021)
- [W-Net: A Facial Feature-Guided Face Super-Resolution Network](https://mlsanity.com/paper/2406.00676/) (2024)
- [A Unified Architecture of Semantic Segmentation and Hierarchical Generative Adversarial Networks for Expression Manipulation](https://mlsanity.com/paper/2112.04603/) (2021)
- [UP-FacE: User-predictable Fine-grained Face Shape Editing](https://mlsanity.com/paper/2403.13972/) (2024)
- [HAIFAI: Human-AI Interaction for Mental Face Reconstruction](https://mlsanity.com/paper/2412.06323/) (2024)
- [Weakly Supervised Pixel-Level Annotation with Visual Interpretability](https://mlsanity.com/paper/2502.17824/) (2025)

## Abstract (arXiv)

We present Mask-guided Generative Adversarial Network (MagGAN) for high-resolution face attribute editing, in which semantic facial masks from a pre-trained face parser are used to guide the fine-grained image editing process. With the introduction of a mask-guided reconstruction loss, MagGAN learns to only edit the facial parts that are relevant to the desired attribute changes, while preserving the attribute-irrelevant regions (e.g., hat, scarf for modification `To Bald'). Further, a novel mask-guided conditioning strategy is introduced to incorporate the influence region of each attribute change into the generator. In addition, a multi-level patch-wise discriminator structure is proposed to scale our model for high-resolution (1024 × 1024) face editing. Experiments on the CelebA benchmark show that the proposed method significantly outperforms prior state-of-the-art approaches in terms of both image quality and editing performance.