# Learning to Hallucinate Face Images via Component Generation and Enhancement

arXiv: https://arxiv.org/abs/1708.00223 · HTML: https://mlsanity.com/paper/1708.00223/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2017.

## Built on by (most cited first, 11 of 11)

- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset](https://mlsanity.com/paper/2110.05031/) (2021)
- [Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition](https://mlsanity.com/paper/2103.13851/) (2021)
- [JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution](https://mlsanity.com/paper/2103.13676/) (2021)
- [InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer](https://mlsanity.com/paper/2307.16227/) (2023)
- [HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars](https://mlsanity.com/paper/2203.14863/) (2022)
- [W-Net: A Facial Feature-Guided Face Super-Resolution Network](https://mlsanity.com/paper/2406.00676/) (2024)
- [From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution](https://mlsanity.com/paper/2108.13584/) (2021)
- [A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions](https://mlsanity.com/paper/2306.03380/) (2023)

## Abstract (arXiv)

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods