IDENet: Implicit Degradation Estimation Network for Efficient Blind Super Resolution

• Published in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 6065 - 6075
• Main Authors: Khan, Asif Hussain, Micheloni, Christian, Martinel, Niki
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.06.2024
• Subjects: Closed-form solutions; Deconvolution; Degradation; Image synthesis; Superresolution; Systematics; Wiener filters
• ISSN: 2160-7516
• DOI: 10.1109/CVPRW63382.2024.00613

Blind image super-resolution (SR) aims to recover high-resolution (HR) images from low-resolution (LR) inputs hindered by unknown degradation. Existing blind SR methods exploit computationally demanding explicit degradation estimators hinging on the availability of ground-truth information about the degradation process, thus introducing a severe limitation in real-world scenarios where this is inherently unattainable. Implicit degradation estimators avoid the need for ground truth but perform poorly. Our model reduces this performance gap with (i) a novel loss component to implicitly learn the degradation kernel from the LR input only, and (ii) a novel learnable Wiener filter module that exploits the learned degradation kernel to efficiently solve the deconvolution task via a closed-form solution formulated in the Fourier domain. Systematic experiments show that our proposed approach outperforms existing implicit blind SR methods (3dB PSNR gain and 8.5% SSIM improvement on average) and achieves comparable performance to explicit blind SR methods (0.6dB and 0.5% difference in PSNR and SSIM, respectively). Remarkably, these results are obtained using 33% and 71% less parameters than implicit and explicit methods.