# Learning Spatial Attention for Face Super-Resolution

arXiv: https://arxiv.org/abs/2012.01211 · HTML: https://mlsanity.com/paper/2012.01211/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2020.

## Built on by (most cited first, 30 of 55)

- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration](https://mlsanity.com/paper/2303.06885/) (2023)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [SeD: Semantic-Aware Discriminator for Image Super-Resolution](https://mlsanity.com/paper/2402.19387/) (2024)
- [Dual Associated Encoder for Face Restoration](https://mlsanity.com/paper/2308.07314/) (2023)
- [CTCNet: A CNN-Transformer Cooperation Network for Face Image Super-Resolution](https://mlsanity.com/paper/2204.08696/) (2022)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network](https://mlsanity.com/paper/2407.19768/) (2024)
- [Deep Face Restoration: A Survey](https://mlsanity.com/paper/2211.02831/) (2022)
- [Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network](https://mlsanity.com/paper/2212.14181/) (2022)
- [Face Super-Resolution Using Stochastic Differential Equations](https://mlsanity.com/paper/2209.12064/) (2022)
- [F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration](https://mlsanity.com/paper/2412.13155/) (2024)
- [Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution](https://mlsanity.com/paper/2205.03777/) (2022)
- [Approaching the Limit of Image Rescaling via Flow Guidance](https://mlsanity.com/paper/2111.05133/) (2021)
- [Iterative Token Evaluation and Refinement for Real-World Super-Resolution](https://mlsanity.com/paper/2312.05616/) (2023)
- [IDLat: An Importance-Driven Latent Generation Method for Scientific Data](https://mlsanity.com/paper/2208.03345/) (2022)
- [Blind Image Super-resolution with Rich Texture-Aware Codebooks](https://mlsanity.com/paper/2310.17188/) (2023)
- [JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution](https://mlsanity.com/paper/2103.13676/) (2021)
- [US-GAN: On the importance of Ultimate Skip Connection for Facial Expression Synthesis](https://mlsanity.com/paper/2112.13002/) (2021)
- [TD-BFR: Truncated Diffusion Model for Efficient Blind Face Restoration](https://mlsanity.com/paper/2503.20537/) (2025)
- [SARGAN: Spatial Attention-based Residuals for Facial Expression Manipulation](https://mlsanity.com/paper/2303.17212/) (2023)
- [Super-Resolving Face Image by Facial Parsing Information](https://mlsanity.com/paper/2304.02923/) (2023)
- [INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration](https://mlsanity.com/paper/2501.14014/) (2025)
- [Robust ID-Specific Face Restoration via Alignment Learning](https://mlsanity.com/paper/2507.10943/) (2025)
- [TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network](https://mlsanity.com/paper/2109.08174/) (2021)
- [Improving Super-Resolution Performance using Meta-Attention Layers](https://mlsanity.com/paper/2110.14638/) (2021)
- [HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars](https://mlsanity.com/paper/2203.14863/) (2022)
- [Meet-in-the-middle: Multi-scale upsampling and matching for cross-resolution face recognition](https://mlsanity.com/paper/2211.15225/) (2022)
- [W-Net: A Facial Feature-Guided Face Super-Resolution Network](https://mlsanity.com/paper/2406.00676/) (2024)

## Abstract (arXiv)

General image super-resolution techniques have difficulties in recovering detailed face structures when applying to low resolution face images. Recent deep learning based methods tailored for face images have achieved improved performance by jointly trained with additional task such as face parsing and landmark prediction. However, multi-task learning requires extra manually labeled data. Besides, most of the existing works can only generate relatively low resolution face images (e.g., 128×128), and their applications are therefore limited. In this paper, we introduce a novel SPatial Attention Residual Network (SPARNet) built on our newly proposed Face Attention Units (FAUs) for face super-resolution. Specifically, we introduce a spatial attention mechanism to the vanilla residual blocks. This enables the convolutional layers to adaptively bootstrap features related to the key face structures and pay less attention to those less feature-rich regions. This makes the training more effective and efficient as the key face structures only account for a very small portion of the face image. Visualization of the attention maps shows that our spatial attention network can capture the key face structures well even for very low resolution faces (e.g., 16×16). Quantitative comparisons on various kinds of metrics (including PSNR, SSIM, identity similarity, and landmark detection) demonstrate the superiority of our method over current state-of-the-arts. We further extend SPARNet with multi-scale discriminators, named as SPARNetHD, to produce high resolution results (i.e., 512×512). We show that SPARNetHD trained with synthetic data cannot only produce high quality and high resolution outputs for synthetically degraded face images, but also show good generalization ability to real world low quality face images.