Cascading Refinement Video Denoising with Uncertainty Adaptivity
This work addresses video denoising for applications requiring high-quality video processing, with incremental improvements in efficiency.
The paper tackles video denoising by introducing a cascading refinement method that simultaneously refines alignment and restores images, achieving state-of-the-art performance on the CRVD dataset. It also reduces computation by 25% on average by using uncertainty maps to avoid redundant processing on easily restored videos.
Accurate alignment is crucial for video denoising. However, estimating alignment in noisy environments is challenging. This paper introduces a cascading refinement video denoising method that can refine alignment and restore images simultaneously. Better alignment enables restoration of more detailed information in each frame. Furthermore, better image quality leads to better alignment. This method has achieved SOTA performance by a large margin on the CRVD dataset. Simultaneously, aiming to deal with multi-level noise, an uncertainty map was created after each iteration. Because of this, redundant computation on the easily restored videos was avoided. By applying this method, the entire computation was reduced by 25% on average.