Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution
Series/Report No.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Part Of
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Start Page
1776
End Page
1785
ISSN
10636919
Date Issued
2023-06
Author(s)
DOI
10.1109/CVPR52729.2023.00177
Abstract
Flow-based methods have demonstrated promising results in addressing the ill-posed nature of super-resolution (SR) by learning the distribution of high-resolution (HR) images with the normalizing flow. However, these methods can only perform a predefined fixed-scale SR, limiting their potential in real-world applications. Meanwhile, arbitrary-scale SR has gained more attention and achieved great progress. Nonetheless, previous arbitrary-scale SR methods ignore the ill-posed problem and train the model with per-pixel L1 loss, leading to blurry SR outputs. In this work, we propose “Local Implicit Normalizing Flow” (LINF) as a unified solution to the above problems. LINF models the distribution of texture details under different scaling factors with normalizing flow. Thus, LINF can generate photo-realistic HR images with rich texture details in arbitrary scale factors. We evaluate LINF with extensive experiments and show that LINF achieves the state-of-the-art perceptual quality compared with prior arbitrary-scale SR methods.
Project(s)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
Event(s)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
SDGs
Publisher
IEEE
Type
conference paper