Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling

TL;DR

This paper introduces a noise modeling-based strategy with shot noise augmentation and dark shading correction to improve learnability and denoising performance for low-light raw image data.

Contribution

It proposes a novel learnability enhancement approach combining noise augmentation and correction techniques for better low-light raw denoising.

Findings

Achieves state-of-the-art denoising results on public datasets.

Effectively increases data volume and reduces noise complexity.

Demonstrates robustness in real imaging scenarios.

Abstract

Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream. However, the limited data volume and complicated noise distribution have constituted a learnability bottleneck for paired real data, which limits the denoising performance of learning-based methods. To address this issue, we present a learnability enhancement strategy to reform paired real data according to noise modeling. Our strategy consists of two efficient techniques: shot noise augmentation (SNA) and dark shading correction (DSC). Through noise model decoupling, SNA improves the precision of data mapping by increasing the data volume and DSC reduces the complexity of data mapping by reducing the noise complexity. Extensive results on the public datasets and real imaging scenarios collectively demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/megvii-research/PMN.