Unsupervised Degradation Representation Learning for Blind Super-Resolution

By Longguang Wang, Yingqian Wang, Xiaoyu Dong, Qingyu Xu, Jungang Yang, Wei An, Yulan Guo. 2021

403 citations recorded by the source corpus.

Most existing CNN-based super-resolution (SR) methods are developed based on an assumption that the degradation is fixed and known (e.g., bicubic downsampling). However, these methods suffer a severe performance drop when the real degradation is different from their assumption. To handle various unknown degradations in real-world applications, previous methods rely on degradation estimation to reconstruct the SR image. Nevertheless, degradation estimation methods are usually time-consuming and may lead to SR failure due to large estimation errors. In this paper, we propose an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation. Specifically, we learn abstract representations to distinguish various degradations in the representation space rather than explicit estimation in the pixel space. Moreover, we introduce a Degradation-Aware SR (DASR) network with flexible adaption to various degradations based on the learned representations. It is demonstrated that our degradation representation learning scheme can extract discriminative representations to obtain accurate degradation information. Experiments on both synthetic and real images show that our network achieves state-of-the-art performance for the blind SR task. Code is available at: https://github.com/LongguangWang/DASR.

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

1. Luc Van Gool
2. Radu Timofte
3. Chen Change Loy
4. Chao Dong
5. Kai Zhang
6. Ming-Hsuan Yang
7. Lei Zhang
8. Ying Shan

In Media Technology

1. Radu Timofte
2. Luc Van Gool
3. Chao Dong
4. Kai Zhang
5. Jingyun Liang
6. Chen Change Loy
7. Lei Zhang
8. Martin Danelljan

Citations in the corpus

• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, background): “Considering the fact that real LR images rarely come with the ground-truth HR, the fourth direction aims at learning with unpaired training data [48].”
• Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data (2021, methodology): “The above two components are performed either separately [2, 54] or jointly (iteratively) [15, 33, 44].”
• Exploiting Diffusion Prior for Real-World Image Super-Resolution (2023, neutral): “In this work, we consider an orthogonal direction of fine-tuning a diffusion model for SR.”
• SwinIR: Image Restoration Using Swin Transformer (2021, neutral): “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 ”
• All-In-One Image Restoration for Unknown Corruption (2022, background): “Third, despite the difference in the task, DASR needs specifying the image super-resolution scale, whereas AirNet does not need any degradation parameters.”
• Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (2021, background): “Since the pioneer work SRCNN [9], many CNNbased models have been proposed in recent years [9, 19, 24, 43, 41, 40, 42, 15, 6, 6, 54, 55, 30, 49, 11, 5, 44, 26, 51, 27, 50].”
• Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild (2024, neutral): “In this Generative Prior.”