Unfolding the Alternating Optimization for Blind Super Resolution
By Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tien-Ping Tan. 2020
340 citations recorded by the source corpus.
Previous methods decompose blind super resolution (SR) problem into two sequential steps: \textit{i}) estimating blur kernel from given low-resolution (LR) image and \textit{ii}) restoring SR image based on estimated kernel. This two-step solution involves two independently trained models, which may not be well compatible with each other. Small estimation error of the first step could cause severe performance drop of the second one. While on the other hand, the first step can only utilize limited information from LR image, which makes it difficult to predict highly accurate blur kernel. Towards these issues, instead of considering these two steps separately, we adopt an alternating optimization algorithm, which can estimate blur kernel and restore SR image in a single model. Specifically, we design two convolutional neural modules, namely \textit{Restorer} and \textit{Estimator}. \textit{Restorer} restores SR image based on predicted kernel, and \textit{Estimator} estimates blur kernel with the help of restored SR image. We alternate these two modules repeatedly and unfold this process to form an end-to-end trainable network. In this way, \textit{Estimator} utilizes information from both LR and SR images, which makes the estimation of blur kernel easier. More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}. Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the-art methods and produce more visually favorable results at much higher speed. The source code is available at this https URL.
Subfields: Computer Vision and Pattern Recognition, Media Technology
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
In Media Technology
Citations in the corpus
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “blind methods propose to fuse the kernel estimation into the network design [15, 28].”
- Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild (2024, background): “Over time, the need for blind IR methods that are not based on specific degradation assumptions has grown [5, 10, 25, 34, 35, 46–48 , 91].”
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data (2021, methodology): “We compare our Real-ESRGAN with several stateof-the-art methods, including ESRGAN [48], DAN [33], CDC [49], RealSR [18] and BSRGAN [53].”
- Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “DAN [92] consists of a chain of alternately stacked restorers and estimators, which are responsible for the restoration of the HR image and the estimation of the blur kernel, respectively.”
- Unsupervised Degradation Representation Learning for Blind Super-Resolution (2021, methodology): “Note that, we do not include DAN [25], USRnet [40] and correction filter [20] for comparison since their degradation model is different from ours.”