# Face Hallucination via Split-Attention in Split-Attention Network

arXiv: https://arxiv.org/abs/2010.11575 · HTML: https://mlsanity.com/paper/2010.11575/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 24 of 24)

- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [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)
- [3D Priors-Guided Diffusion for Blind Face Restoration](https://mlsanity.com/paper/2409.00991/) (2024)
- [JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution](https://mlsanity.com/paper/2103.13676/) (2021)
- [AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Prior](https://mlsanity.com/paper/2410.09864/) (2024)
- [Super-Resolving Face Image by Facial Parsing Information](https://mlsanity.com/paper/2304.02923/) (2023)
- [TANet: A new Paradigm for Global Face Super-resolution via Transformer-CNN Aggregation Network](https://mlsanity.com/paper/2109.08174/) (2021)
- [Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors](https://mlsanity.com/paper/2210.06002/) (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)
- [LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolution](https://mlsanity.com/paper/2411.09293/) (2024)
- [Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint](https://mlsanity.com/paper/2110.01880/) (2021)
- [Generative Iris Prior Embedded Transformer for Iris Restoration](https://mlsanity.com/paper/2407.00261/) (2024)
- [CLIP-aware Domain-Adaptive Super-Resolution](https://mlsanity.com/paper/2505.12391/) (2025)
- [FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution](https://mlsanity.com/paper/2506.14121/) (2025)
- [A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions](https://mlsanity.com/paper/2306.03380/) (2023)
- [Attention-Guided Multi-scale Interaction Network for Face Super-Resolution](https://mlsanity.com/paper/2409.00591/) (2024)
- [Prior Knowledge Distillation Network for Face Super-Resolution](https://mlsanity.com/paper/2409.14385/) (2024)
- [AffectSRNet : Facial Emotion-Aware Super-Resolution Network](https://mlsanity.com/paper/2502.09932/) (2025)
- [Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks](https://mlsanity.com/paper/2511.16341/) (2025)
- [SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution](https://mlsanity.com/paper/2601.01406/) (2026)

## Abstract (arXiv)

Recently, convolutional neural networks (CNNs) have been widely employed to promote the face hallucination due to the ability to predict high-frequency details from a large number of samples. However, most of them fail to take into account the overall facial profile and fine texture details simultaneously, resulting in reduced naturalness and fidelity of the reconstructed face, and further impairing the performance of downstream tasks (e.g., face detection, facial recognition). To tackle this issue, we propose a novel external-internal split attention group (ESAG), which encompasses two paths responsible for facial structure information and facial texture details, respectively. By fusing the features from these two paths, the consistency of facial structure and the fidelity of facial details are strengthened at the same time. Then, we propose a split-attention in split-attention network (SISN) to reconstruct photorealistic high-resolution facial images by cascading several ESAGs. Experimental results on face hallucination and face recognition unveil that the proposed method not only significantly improves the clarity of hallucinated faces, but also encourages the subsequent face recognition performance substantially. Codes have been released at https://github.com/mdswyz/SISN-Face-Hallucination.