Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
This addresses the problem of inconsistent quality in video enhancement for applications requiring high-resolution, clean, and well-lit video output, representing a novel integration rather than an incremental improvement.
The paper tackled the challenge of performing video super-resolution on low-light and noisy videos by introducing Deep Parametric 3D Filters (DP3DF), which jointly handle denoising, illumination enhancement, and super-resolution in a single network, achieving top PSNR and user ratings on real datasets with fast run time.
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The current best solution is to subsequently employ best models of video SR, denoising, and illumination enhancement, but doing so often lowers the image quality, due to the inconsistency between the models. This paper presents a new parametric representation called the Deep Parametric 3D Filters (DP3DF), which incorporates local spatiotemporal information to enable simultaneous denoising, illumination enhancement, and SR efficiently in a single encoder-and-decoder network. Also, a dynamic residual frame is jointly learned with the DP3DF via a shared backbone to further boost the SR quality. We performed extensive experiments, including a large-scale user study, to show our method's effectiveness. Our method consistently surpasses the best state-of-the-art methods on all the challenging real datasets with top PSNR and user ratings, yet having a very fast run time.