# Characteristic Regularisation for Super-Resolving Face Images

arXiv: https://arxiv.org/abs/1912.12987 · HTML: https://mlsanity.com/paper/1912.12987/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Real-World Super-Resolution of Face-Images from Surveillance Cameras](https://mlsanity.com/paper/2102.03113/) (2021)
- [Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior](https://mlsanity.com/paper/2205.14377/) (2022)
- [Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints](https://mlsanity.com/paper/2609.01014/) (2026)

## Abstract (arXiv)

Existing facial image super-resolution (SR) methods focus mostly on improving artificially down-sampled low-resolution (LR) imagery. Such SR models, although strong at handling artificial LR images, often suffer from significant performance drop on genuine LR test data. Previous unsupervised domain adaptation (UDA) methods address this issue by training a model using unpaired genuine LR and HR data as well as cycle consistency loss formulation. However, this renders the model overstretched with two tasks: consistifying the visual characteristics and enhancing the image resolution. Importantly, this makes the end-to-end model training ineffective due to the difficulty of back-propagating gradients through two concatenated CNNs. To solve this problem, we formulate a method that joins the advantages of conventional SR and UDA models. Specifically, we separate and control the optimisations for characteristics consistifying and image super-resolving by introducing Characteristic Regularisation (CR) between them. This task split makes the model training more effective and computationally tractable. Extensive evaluations demonstrate the performance superiority of our method over state-of-the-art SR and UDA models on both genuine and artificial LR facial imagery data.