# BFRFormer: Transformer-based generator for Real-World Blind Face Restoration

arXiv: https://arxiv.org/abs/2402.18811 · HTML: https://mlsanity.com/paper/2402.18811/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 29 Feb 2024.

## Builds on (most cited first, 23 of 23)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](https://mlsanity.com/paper/2012.00739/) (2020)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder](https://mlsanity.com/paper/2205.06803/) (2022)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [Progressive Semantic-Aware Style Transformation for Blind Face Restoration](https://mlsanity.com/paper/2009.08709/) (2020)
- [Learning Warped Guidance for Blind Face Restoration](https://mlsanity.com/paper/1804.04829/) (2018)
- [RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2201.06374/) (2022)
- [Deep Semantic Face Deblurring](https://mlsanity.com/paper/1803.03345/) (2018)
- [DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration](https://mlsanity.com/paper/2303.06885/) (2023)
- [Progressive Face Super-Resolution via Attention to Facial Landmark](https://mlsanity.com/paper/1908.08239/) (2019)
- [HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment](https://mlsanity.com/paper/2005.05005/) (2020)
- [Exemplar Guided Face Image Super-Resolution without Facial Landmarks](https://mlsanity.com/paper/1906.07078/) (2019)
- [Learning Dual Memory Dictionaries for Blind Face Restoration](https://mlsanity.com/paper/2210.08160/) (2022)
- [Deep Cascaded Bi-Network for Face Hallucination](https://mlsanity.com/paper/1607.05046/) (2016)

## Built on by (most cited first, 1 of 1)

- [Binary Diffusion Probabilistic Model](https://mlsanity.com/paper/2501.13915/) (2025)

## Abstract (arXiv)

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain over-smoothed results and lose identity-preserved details when the degradation is severe. It is observed that this is attributed to short-range dependencies, the intrinsic limitation of convolutional neural networks. To model long-range dependencies, we propose a Transformer-based blind face restoration method, named BFRFormer, to reconstruct images with more identity-preserved details in an end-to-end manner. In BFRFormer, to remove blocking artifacts, the wavelet discriminator and aggregated attention module are developed, and spectral normalization and balanced consistency regulation are adaptively applied to address the training instability and over-fitting problem, respectively. Extensive experiments show that our method outperforms state-of-the-art methods on a synthetic dataset and four real-world datasets. The source code, Casia-Test dataset, and pre-trained models are released at https://github.com/s8Znk/BFRFormer.