Self-Supervised Deep Blind Video Super-Resolution
This addresses the challenge of video super-resolution for real-world applications where obtaining paired training data is difficult, though it is incremental as it builds on existing self-supervised and optical flow techniques.
The paper tackles the problem of video super-resolution in real-world scenarios where degradation processes are complex and paired high-resolution/low-resolution data is scarce, by proposing a self-supervised method that estimates blur kernels and restores high-resolution videos from low-resolution inputs, achieving favorable performance against state-of-the-art methods on benchmarks and real-world videos.
Existing deep learning-based video super-resolution (SR) methods usually depend on the supervised learning approach, where the training data is usually generated by the blurring operation with known or predefined kernels (e.g., Bicubic kernel) followed by a decimation operation. However, this does not hold for real applications as the degradation process is complex and cannot be approximated by these idea cases well. Moreover, obtaining high-resolution (HR) videos and the corresponding low-resolution (LR) ones in real-world scenarios is difficult. To overcome these problems, we propose a self-supervised learning method to solve the blind video SR problem, which simultaneously estimates blur kernels and HR videos from the LR videos. As directly using LR videos as supervision usually leads to trivial solutions, we develop a simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration. In addition, we introduce an optical flow estimation module to exploit the information from adjacent frames for HR video restoration. Experiments show that our method performs favorably against state-of-the-art ones on benchmarks and real-world videos.