Deep Blind Video Super-resolution
This addresses the issue of over-smoothed outputs in video super-resolution for applications like video enhancement, though it is incremental as it builds on existing CNN approaches.
The authors tackled the problem of video super-resolution by modeling unknown blur kernels, which existing methods assume are known, and developed a deep CNN that estimates motion blur and uses adjacent frames to restore sharp details, resulting in clearer images with finer structural details and favorable performance against state-of-the-art methods.
Existing video super-resolution (SR) algorithms usually assume that the blur kernels in the degradation process are known and do not model the blur kernels in the restoration. However, this assumption does not hold for video SR and usually leads to over-smoothed super-resolved images. In this paper, we propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed deep CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. The motion blur estimation module is used to provide reliable blur kernels. With the estimated blur kernel, we develop an image deconvolution method based on the image formation model of video SR to generate intermediate latent images so that some sharp image contents can be restored well. However, the generated intermediate latent images may contain artifacts. To generate high-quality images, we use the motion estimation module to explore the information from adjacent frames, where the motion estimation can constrain the deep CNN model for better image restoration. We show that the proposed algorithm is able to generate clearer images with finer structural details. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods.