# Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing

arXiv: https://arxiv.org/abs/2009.07827 · HTML: https://mlsanity.com/paper/2009.07827/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [DiffusionRig: Learning Personalized Priors for Facial Appearance Editing](https://mlsanity.com/paper/2304.06711/) (2023)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [MyStyle: A Personalized Generative Prior](https://mlsanity.com/paper/2203.17272/) (2022)
- [InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention](https://mlsanity.com/paper/2412.06753/) (2024)
- [Personalized Restoration via Dual-Pivot Tuning](https://mlsanity.com/paper/2312.17234/) (2023)
- [HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars](https://mlsanity.com/paper/2203.14863/) (2022)
- [Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints](https://mlsanity.com/paper/2609.01014/) (2026)

## Abstract (arXiv)

Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof. This, by itself, is an ill-posed problem, as the high-frequency information is missing in the low-resolution input and needs to be hallucinated, based on prior knowledge about the image content. Rather than relying on a generic face prior, in this paper, we explore the use of a set of exemplars, i.e. other high-resolution images of the same person. These guide the neural network as we condition the output on them. Multiple exemplars work better than a single one. To combine the information from multiple exemplars effectively, we introduce a pixel-wise weight generation module. Besides standard face super-resolution, our method allows to perform subtle face editing simply by replacing the exemplars with another set with different facial features. A user study is conducted and shows the super-resolved images can hardly be distinguished from real images on the CelebA dataset. A qualitative comparison indicates our model outperforms methods proposed in the literature on the CelebA and WebFace dataset.