# Semantic-Guided Two-Stage GAN for Face Inpainting with Hybrid Perceptual Encoding

arXiv: https://arxiv.org/abs/2512.05039 · HTML: https://mlsanity.com/paper/2512.05039/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [Pluralistic Image Completion](https://mlsanity.com/paper/1903.04227/) (2019)
- [Coherent Semantic Attention for Image Inpainting](https://mlsanity.com/paper/1905.12384/) (2019)
- [Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting](https://mlsanity.com/paper/1904.07475/) (2019)
- [Foreground-aware Image Inpainting](https://mlsanity.com/paper/1901.05945/) (2019)
- [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://mlsanity.com/paper/2104.01431/) (2021)
- [Shift-Net: Image Inpainting via Deep Feature Rearrangement](https://mlsanity.com/paper/1801.09392/) (2018)
- [Contextual-based Image Inpainting: Infer, Match, and Translate](https://mlsanity.com/paper/1711.08590/) (2017)
- [Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2403.19898/) (2024)

## Abstract (arXiv)

Facial Image inpainting aim is to restore the missing or corrupted regions in face images while preserving identity, structural consistency and photorealistic image quality, a task specifically created for photo restoration. Though there are recent lot of advances in deep generative models, existing methods face problems with large irregular masks, often producing blurry textures on the edges of the masked region, semantic inconsistencies, or unconvincing facial structures due to direct pixel level synthesis approach and limited exploitation of facial priors. In this paper we propose a novel architecture, which address these above challenges through semantic-guided hierarchical synthesis. Our approach starts with a method that organizes and synthesizes information based on meaning, followed by refining the texture. This process gives clear insights into the facial structure before we move on to creating detailed images. In the first stage, we blend two techniques: one that focuses on local features with CNNs and global features with Vision Transformers. This helped us create clear and detailed semantic layouts. In the second stage, we use a Multi-Modal Texture Generator to refine these layouts by pulling in information from different scales, ensuring everything looks cohesive and consistent. The architecture naturally handles arbitrary mask configurations through dynamic attention without maskspecific training. Experiment on two datasets CelebA-HQ and FFHQ shows that our model outperforms other state-of-the-art methods, showing improvements in metrics like LPIPS, PSNR, and SSIM. It produces visually striking results with better semantic preservation, in challenging large-area inpainting situations.