Manuscript Number : IJSRSET229344

Video Regeneration and Quality Enhancer using GFP-GAN

Authors(5) :-Girija V, Sunny Nehra, Himanshu Kumar, Avinash Yadav, Karan R

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in real-world scenarios. In this work, we propose GFP-GAN that leverages rich and diverse priors encapsulated in a pretrained face GAN for blind face restoration. This Generative Facial Prior (GFP) is incorporated into the face restoration process via spatial feature transform layers, which allow our method to achieve a good balance of realness and fidelity. Thanks to the powerful generative facial prior and delicate designs, our GFP-GAN could jointly restore facial details and enhance colors with just a single forward pass, while GAN inversion methods require image-specific optimization at inference. Extensive experiments show that our method achieves superior performance to prior art on both synthetic and real-world datasets.

Authors and Affiliations

Girija V
Assistant Professor, CiTeh, Bangalore, Karnataka, India
Sunny Nehra
Student, CiTech, Bangalore, Karnataka, India
Himanshu Kumar
Student, CiTech, Bangalore, Karnataka, India
Avinash Yadav
Student, CiTech, Bangalore, Karnataka, India
Karan R
Student, CiTech, Bangalore, Karnataka, India

GFP-GAN, Generative Facial Prior, Video Regeneration Quality Enhancer

  1. Rameen Abdal, Yipeng Qin, and Peter Wonka. Image2stylegan: How to embed images into the stylegan latent space? In ICCV, 2019.
  2. Yochai Blau, Roey Mechrez, Radu Timofte, Tomer Michaeli, and Lihi Zelnik-Manor. The 2018 pirm challenge on perceptual image super-resolution. In ECCVW, 2018.
  3. Andrew Brock, Jeff Donahue, and Karen Simonyan. Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096, 2018.
  4. Adrian Bulat and Georgios Tzimiropoulos. Super-fan: Integrated facial landmark localization and super-resolution of real-world low-resolution faces in arbitrary poses with gans. In CVPR, 2018.
  5. Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, and Guanbin Li. Attention-aware face hallucination via deep reinforcement learning. In CVPR, 2017.
  6. Jingwen Chen, Jiawei Chen, Hongyang Chao, and Ming Yang. Image blind denoising with generative adversarial network-based noise modeling. In CVPR, 2018.
  7. Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, and Jiashi Feng. Dual path networks. In NeurIPS, 2017.2

Publication Details

Published in : Volume 9 | Issue 3 | May-June 2022
Date of Publication : 2022-06-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 148-151
Manuscript Number : IJSRSET229344
Publisher : Technoscience Academy

Print ISSN : 2395-1990, Online ISSN : 2394-4099

Cite This Article :

Girija V, Sunny Nehra, Himanshu Kumar, Avinash Yadav, Karan R, " Video Regeneration and Quality Enhancer using GFP-GAN, International Journal of Scientific Research in Science, Engineering and Technology(IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 9, Issue 3, pp.148-151, May-June-2022. Available at doi : https://doi.org/10.32628/IJSRSET229344      Journal URL : https://res.ijsrset.com/IJSRSET229344

Article Preview