# Component Attention Guided Face Super-Resolution Network: CAGFace

arXiv: https://arxiv.org/abs/1910.08761 · HTML: https://mlsanity.com/paper/1910.08761/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2019.

## Built on by (most cited first, 14 of 14)

- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Dual Associated Encoder for Face Restoration](https://mlsanity.com/paper/2308.07314/) (2023)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [Deep Face Restoration: A Survey](https://mlsanity.com/paper/2211.02831/) (2022)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [Octuplet Loss: Make Face Recognition Robust to Image Resolution](https://mlsanity.com/paper/2207.06726/) (2022)
- [ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition](https://mlsanity.com/paper/2407.14972/) (2024)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [Frequency Aware Face Hallucination Generative Adversarial Network with Semantic Structural Constraint](https://mlsanity.com/paper/2110.01880/) (2021)
- [Boosting Unconstrained Face Recognition with Targeted Style Adversary](https://mlsanity.com/paper/2408.07642/) (2024)
- [A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions](https://mlsanity.com/paper/2306.03380/) (2023)
- [Face Mask Removal with Region-attentive Face Inpainting](https://mlsanity.com/paper/2409.06845/) (2024)
- [Co-learning Single-Step Diffusion Upsampler and Downsampler with Two Discriminators and Distillation](https://mlsanity.com/paper/2410.07663/) (2024)
- [AffectSRNet : Facial Emotion-Aware Super-Resolution Network](https://mlsanity.com/paper/2502.09932/) (2025)

## Abstract (arXiv)

To make the best use of the underlying structure of faces, the collective information through face datasets and the intermediate estimates during the upsampling process, here we introduce a fully convolutional multi-stage neural network for 4× super-resolution for face images. We implicitly impose facial component-wise attention maps using a segmentation network to allow our network to focus on face-inherent patterns. Each stage of our network is composed of a stem layer, a residual backbone, and spatial upsampling layers. We recurrently apply stages to reconstruct an intermediate image, and then reuse its space-to-depth converted versions to bootstrap and enhance image quality progressively. Our experiments show that our face super-resolution method achieves quantitatively superior and perceptually pleasing results in comparison to state of the art.