Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments

TL;DR

This paper introduces Rawgment, a RAW image augmentation technique that accounts for noise and ISP non-linearity, significantly improving recognition accuracy in difficult environments without complex datasets.

Contribution

We propose a noise-accounted RAW augmentation method that applies color jitter and blur before ISP processing, enhancing realism and robustness in recognition models.

Findings

Doubles recognition accuracy in challenging environments

Effective augmentation without complex datasets

Calibrates noise domain gap for realism

Abstract

Image recognition models that work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating training datasets for such environments is expensive and hard due to the difficulties of data collection and annotation. It is desirable if we could get a robust model without the need for hard-to-obtain datasets. One simple approach is to apply data augmentation such as color jitter and blur to standard RGB (sRGB) images in simple scenes. Unfortunately, this approach struggles to yield realistic images in terms of pixel intensity and noise distribution due to not considering the non-linearity of Image Signal Processors (ISPs) and noise characteristics of image sensors. Instead, we propose a noise-accounted RAW image augmentation method. In essence, color jitter and blur augmentation are applied to a RAW image before applying non-linear ISP, resulting in realistic intensity. Furthermore, we introduce a noise amount alignment method that calibrates the domain gap in the noise property caused by the augmentation. We show that our proposed noise-accounted RAW augmentation method doubles the image recognition accuracy in challenging environments only with simple training data.