# Face Hallucination with Finishing Touches

arXiv: https://arxiv.org/abs/2002.03308 · HTML: https://mlsanity.com/paper/2002.03308/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2020.

## Built on by (most cited first, 10 of 10)

- [Learning Dual Memory Dictionaries for Blind Face Restoration](https://mlsanity.com/paper/2210.08160/) (2022)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Joint Face Image Restoration and Frontalization for Recognition](https://mlsanity.com/paper/2105.09907/) (2021)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation](https://mlsanity.com/paper/2304.10066/) (2023)
- [Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar](https://mlsanity.com/paper/2103.08863/) (2021)
- [Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails](https://mlsanity.com/paper/2108.00602/) (2021)
- [CLIP-SR: Collaborative Linguistic and Image Processing for Super-Resolution](https://mlsanity.com/paper/2412.11609/) (2024)
- [Automated Deepfake Detection](https://mlsanity.com/paper/2106.10705/) (2021)
- [VerA: Versatile Anonymization Applicable to Clinical Facial Photographs](https://mlsanity.com/paper/2312.02124/) (2023)

## Abstract (arXiv)

Obtaining a high-quality frontal face image from a low-resolution (LR) non-frontal face image is primarily important for many facial analysis applications. However, mainstreams either focus on super-resolving near-frontal LR faces or frontalizing non-frontal high-resolution (HR) faces. It is desirable to perform both tasks seamlessly for daily-life unconstrained face images. In this paper, we present a novel Vivid Face Hallucination Generative Adversarial Network (VividGAN) for simultaneously super-resolving and frontalizing tiny non-frontal face images. VividGAN consists of coarse-level and fine-level Face Hallucination Networks (FHnet) and two discriminators, i.e., Coarse-D and Fine-D. The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i.e., fine-grained facial components, to attain a frontal HR face image with authentic details. In the fine-level FHnet, we also design a facial component-aware module that adopts the facial geometry guidance as clues to accurately align and merge the frontal coarse HR face and prior information. Meanwhile, two-level discriminators are designed to capture both the global outline of a face image as well as detailed facial characteristics. The Coarse-D enforces the coarsely hallucinated faces to be upright and complete while the Fine-D focuses on the fine hallucinated ones for sharper details. Extensive experiments demonstrate that our VividGAN achieves photo-realistic frontal HR faces, reaching superior performance in downstream tasks, i.e., face recognition and expression classification, compared with other state-of-the-art methods.