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

10/28/2022
by   Masakazu Yoshimura, et al.
0

Image recognition models that can work in challenging environments (e.g., extremely dark, blurry, or high dynamic range conditions) must be useful. However, creating a training dataset 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 of hard-to-obtain dataset. 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 Processor (ISP) and noise characteristics of an image sensor. 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, yielding realistic intensity. Furthermore, we introduce a noise amount alignment method that calibrates the domain gap in 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.

READ FULL TEXT

page 6

page 12

research
09/06/2022

Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation

Although Convolutional Neural Networks (CNNs) have high accuracy in imag...
research
05/22/2020

Polarimetric image augmentation

Robotics applications in urban environments are subject to obstacles tha...
research
04/19/2022

Core Box Image Recognition and its Improvement with a New Augmentation Technique

Most methods for automated full-bore rock core image analysis (descripti...
research
11/02/2020

SapAugment: Learning A Sample Adaptive Policy for Data Augmentation

Data augmentation methods usually apply the same augmentation (or a mix ...
research
06/10/2021

Data augmentation to improve robustness of image captioning solutions

In this paper, we study the impact of motion blur, a common quality flaw...
research
07/20/2023

Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors

As the physical size of recent CMOS image sensors (CIS) gets smaller, th...
research
09/05/2023

RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image

High dynamic range (HDR) images capture much more intensity levels than ...

Please sign up or login with your details

Forgot password? Click here to reset