A Multi-scale Video Denoising Algorithm for Raw Image

TL;DR

This paper introduces a multi-scale video denoising algorithm for raw images that leverages a CNN with implicit motion estimation, achieving superior denoising quality with minimal computational cost.

Contribution

It proposes a novel multi-stage CNN-based video denoising method that implicitly estimates motion, improving raw video quality efficiently.

Findings

Outperforms traditional denoising algorithms in quality.

Requires less computation and bandwidth than comparable deep learning methods.

Effectively handles motion in raw video denoising.

Abstract

Video denoising for raw image has always been the difficulty of camera image processing. On the one hand, image denoising performance largely determines the image quality, moreover denoising effect in raw image will affect the accuracy of the following operations of ISP processing flow. On the other hand, compared with image, video have motion information in time sequence, thus motion estimation which is complex and computationally expensive is needed in video denoising. In view of the above problems, this paper proposes a video denoising algorithm for raw image, performing multiple cascading processing stages on raw-RGB image based on convolutional neural network, and carries out implicit motion estimation in the network. The denoising performance is far superior to that of traditional algorithms with minimal computation and bandwidth, and has computational advantages compared with most deep learning algorithms.