# Self-Enhanced Convolutional Network for Facial Video Hallucination

arXiv: https://arxiv.org/abs/1911.11136 · HTML: https://mlsanity.com/paper/1911.11136/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2019.

## Built on by (most cited first, 5 of 5)

- [VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution](https://mlsanity.com/paper/2205.03409/) (2022)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Cross-Modality High-Frequency Transformer for MR Image Super-Resolution](https://mlsanity.com/paper/2203.15314/) (2022)
- [Towards Real-world Video Face Restoration: A New Benchmark](https://mlsanity.com/paper/2404.19500/) (2024)
- [Dual-domain Adaptation Networks for Realistic Image Super-resolution](https://mlsanity.com/paper/2511.17217/) (2025)

## Abstract (arXiv)

As a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. However, the direct migration of existing methods to video is still difficult to achieve good performance due to its lack of alignment and consistency modelling in temporal domain. Taking advantage of high inter-frame dependency in videos, we propose a self-enhanced convolutional network for facial video hallucination. It is implemented by making full usage of preceding super-resolved frames and a temporal window of adjacent low-resolution frames. Specifically, the algorithm first obtains the initial high-resolution inference of each frame by taking into consideration a sequence of consecutive low-resolution inputs through temporal consistency modelling. It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames. Quantitative and qualitative evaluations demonstrate the superiority of the proposed algorithm against state-of-the-art methods. Moreover, our algorithm also achieves excellent performance in the task of general video super-resolution in a single-shot setting.