Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
By Jingyun Liang, Andreas Lugmayr, Kai Zhang, Martin Danelljan, Luc Van Gool, Radu Timofte. 2021
125 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Radu Timofte
- Luc Van Gool
- Kai Zhang
- Jingyun Liang
- Chen Change Loy
- Lei Zhang
- Ming-Hsuan Yang
- Wangmeng Zuo
Citations in the corpus
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, background): “With the advance of deep neural networks (DNNs), there is a dramatic upsurge of using feedforward DNNs for fast and effective SISR [17, 23, 25, 27, 49, 61].”
- SwinIR: Image Restoration Using Swin Transformer (2021, unknown): “Since pioneering work SRCNN [18] (for image SR), DnCNN [90] (for image denoising) and ARCNN [17] (for JPEG compression artifact reduction), a flurry of CNN-based models have been proposed to improve model representation ability by using larger and deeper neural network architecture designs, such as ”