Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
METADATA ONLY
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Normalizing flows have recently demonstrated promising results for low-level vision tasks. For image super-resolution (SR), it learns to predict diverse photo-realistic high-resolution (HR) images from the low-resolution (LR) image rather than learning a deterministic mapping. For image rescaling, it achieves high accuracy by jointly modelling the downscaling and upscaling processes. While existing approaches employ specialized techniques for these two tasks, we set out to unify them in a single formulation. In this paper, we propose the hierarchical conditional flow (HCFlow) as a unified framework for image SR and image rescaling. More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously. In particular, the high-frequency component is conditional on the LR image in a hierarchical manner. To further enhance the performance, other losses such as perceptual loss and GAN loss are combined with the commonly used negative log-likelihood loss in training. Extensive experiments on general image SR, face image SR and image rescaling have demonstrated that the proposed HCFlow achieves state-of-the-art performance in terms of both quantitative metrics and visual quality.
Permanent link
Publication status
published
External links
Editor
Book title
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Journal / series
Volume
Pages / Article No.
4076 - 4085
Publisher
IEEE
Event
18th International Conference on Computer Vision (ICCV 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Low-level and physics-based vision
Organisational unit
03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus)