Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network

TL;DR

This paper introduces an efficient burst raw image denoising system that combines variance stabilization, explicit alignment, and a multi-frequency denoising network, achieving high-quality results with low computational cost suitable for smartphones.

Contribution

It proposes a novel three-stage burst denoising framework that integrates noise prior, uses conventional alignment, and employs a sequential multi-frequency denoising strategy, improving efficiency and performance.

Findings

Outperforms state-of-the-art methods on synthetic and real datasets.

Reduces computational cost significantly compared to existing approaches.

Enables deployment on smartphones due to low complexity and high quality.

Abstract

With the growing popularity of smartphones, capturing high-quality images is of vital importance to smartphones. The cameras of smartphones have small apertures and small sensor cells, which lead to the noisy images in low light environment. Denoising based on a burst of multiple frames generally outperforms single frame denoising but with the larger compututional cost. In this paper, we propose an efficient yet effective burst denoising system. We adopt a three-stage design: noise prior integration, multi-frame alignment and multi-frame denoising. First, we integrate noise prior by pre-processing raw signals into a variance-stabilization space, which allows using a small-scale network to achieve competitive performance. Second, we observe that it is essential to adopt an explicit alignment for burst denoising, but it is not necessary to integrate a learning-based method to perform multi-frame alignment. Instead, we resort to a conventional and efficient alignment method and combine it with our multi-frame denoising network. At last, we propose a denoising strategy that processes multiple frames sequentially. Sequential denoising avoids filtering a large number of frames by decomposing multiple frames denoising into several efficient sub-network denoising. As for each sub-network, we propose an efficient multi-frequency denoising network to remove noise of different frequencies. Our three-stage design is efficient and shows strong performance on burst denoising. Experiments on synthetic and real raw datasets demonstrate that our method outperforms state-of-the-art methods, with less computational cost. Furthermore, the low complexity and high-quality performance make deployment on smartphones possible.