Rethinking Pixel-Wise Loss for Face Super-Resolution
- 31 January 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
Face super-resolution has become much attractive in terms of its applications, i.e., video surveillance, and face identification system. However, it is difficult to reconstruct super-resolved images from low-resolution images due to the lack of information in missing pixels. To achieve it, most state-of-the-art methods have used deep neural networks to compensate for missing parts in the reconstruction process by optimizing pixel-wise loss functions. In these methods, various basic pixel-wise loss functions were utilized in image-level and feature-level, but there did not exist the analysis of pixel-wise functions. In this paper, we analyze pixel-wise loss functions in different image domains and feature-level to explore the effects of the loss function in face super-resolution. Furthermore, we provide extensive experiments on CelebA to rethink existing pixel-wise loss and make the best combination of existing loss functions.Keywords
Funding Information
- National Research Foundation of Korea (NRF) (2020R1A2C101215911)
This publication has 9 references indexed in Scilit:
- Face Hallucination Using Cascaded Super-Resolution and Identity PriorsIEEE Transactions on Image Processing, 2020
- SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face HallucinationIEEE Transactions on Image Processing, 2019
- Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses with GANs2018
- FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors2018
- VGGFace2: A Dataset for Recognising Faces across Pose and Age2018
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Going deeper with convolutions2015
- YUV vs RGB—Choosing a Color Space for Human-Machine Interaction2014
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004