Real-World Super-Resolution via Kernel Estimation and Noise Injection

By Xiaozhong Ji, Yun Cao, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang. 2020

360 citations recorded by the source corpus.

Recent state-of-the-art super-resolution methods have achieved impressive performance on ideal datasets regardless of blur and noise. However, these methods always fail in real-world image super-resolution, since most of them adopt simple bicubic downsampling from high-quality images to construct Low-Resolution (LR) and HighResolution (HR) pairs for training which may lose track of frequency-related details. To address this issue, we focus on designing a novel degradation framework for real- world images by estimating various blur kernels as well as real noise distributions. Based on our novel degradation framework, we can acquire LR images sharing a common domain with real-world images. Then, we propose a real- world super-resolution model aiming at better perception. Extensive experiments on synthetic noise data and real- world images demonstrate that our method outperforms the state-of-the-art methods, resulting in lower noise and better visual quality. In addition, our method is the winner of NTIRE 2020 Challenge on both tracks of Real-World Super-Resolution, which significantly outperforms other competitors by large margins.

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

1. Luc Van Gool
2. Chen Change Loy
3. Radu Timofte
4. Ming-Hsuan Yang
5. Yu Qiao
6. Lei Zhang
7. Dacheng Tao
8. Xiaogang Wang

Citations in the corpus

• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (2021, methodology): “Along another line of blind SISR work with unpaired LR/HR training data, the kernel and the noise are first extracted from the LR images and then used to synthesize LR images from the HR images for paired training [20].”
• ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (2023, methodology): “We evaluate the effectiveness of ResShift in comparison to seven recent SR methods, namely ESRGAN [62], RealSR-JPEG [63], BSRGAN [18], RealESRGAN [19], SwinIR [20], DASR [21], and LDM [11].”
• MambaIR: A Simple Baseline for Image Restoration with State-Space Model (2024, methodology): “6: Qualitative comparison with RealSR [32], ESRGAN [68], BSRGAN [80], Real-ESRGAN [67], and SwinIR [41] on real image super-resolution with scale × 4.”
• SwinIR: Image Restoration Using Swin Transformer (2021, methodology): “Since there is no ground-truth high-quality images, we only provide visual comparison with representative bicubic model ESRGAN [81] and state-of-the-art realworld image SR models FSSR [24], RealSR [37] and BSRGAN [89].”
• Exploiting Diffusion Prior for Real-World Image Super-Resolution (2023, neutral): “Datasets Metrics RealSR [30] BSRGAN [77] Real-ESRGAN+ [64] DASR [38] FeMaSR [8] LDM [51] StableSR (w = 0.”
• 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].”
• SinSR: Diffusion-Based Image Super-Resolution in a Single Step (2023, methodology): “We compare our method with several representative SR models, including RealSR-JPEG [12], ESRGAN [40], BSRGAN [47], SwinIR [18], RealESR-GAN [ 41], DASR [19], LDM [32], and ResShift [46].”
• NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results (2020, background): “The team Impressionism proposes a novel framework, introduced in [35], to improve the robustness of the superresolution model on real images, which usually fails when trained on bicubic downsampled data.”
• Real-World Single Image Super-Resolution: A Brief Review (2021, methodology): “22The source code of RSRKN [98] is available at https://github.”
• DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior (2023, methodology): “It is observed that our DiffBIR ( s = 0 ) obtains the best scores across all metrics on both the widely used RealSRSet [73] and our collected Real47.”
• Unfolding the Alternating Optimization for Blind Super Resolution (2020, neutral): “[20] - 1st in NITRE’20 track 1 / / 25.”