Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
This work addresses the need for improved image quality in low-level vision tasks, offering a unified solution for both super-resolution and rescaling, though it appears incremental as it builds on existing normalizing flow techniques.
The paper tackles the problem of image super-resolution and rescaling by proposing a unified framework called Hierarchical Conditional Flow (HCFlow), which learns a bijective mapping between high-resolution and low-resolution images, achieving state-of-the-art performance in quantitative metrics and visual quality across general and face image tasks.
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.