Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

TL;DR

This paper introduces HCFlow, a unified hierarchical conditional flow model that effectively handles both image super-resolution and rescaling by modeling the joint distribution of images and their high-frequency details, achieving state-of-the-art results.

Contribution

The paper presents HCFlow, the first unified framework combining super-resolution and rescaling tasks within a single flow-based model, incorporating hierarchical conditioning and multiple loss functions.

Findings

Achieves state-of-the-art performance on various image SR benchmarks.

Effectively models high-frequency details conditioned on low-resolution images.

Demonstrates versatility across general and face image SR tasks.

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.