Paper Info
Title
Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
Abstract
In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image de noising. Compared with traditional RGB image denoising, performing this task on direct camera sensor readings presents new challenges such as how to effectively handle various Bayer patterns from different data sources, and subsequently how to perform valid data augmentation with raw images. To address the first problem, we propose a Bayer pattern unification (BayerUnify) method to unify different Bayer patterns. This allows us to fully utilize a heterogeneous dataset to train a single denoising model instead of training one model for each pattern. Furthermore, while it is essential to augment the dataset to improve model generalization and performance, we discovered that it is error-prone to modify raw images by adapting augmentation methods designed for RGB images. Towards this end, we present a Bayer preserving augmentation (BayerAug) method as an effective approach for raw image augmentation. Combining these data processing technqiues with a modified U-Net, our method achieves a PSNR of 52.11 and a SSIM of 0.9969 in NTIRE 2019 Real Image Denoising Challenge, demonstrating the state-of-the-art performance.
Year
DOI
Venue
2019
10.1109/CVPRW.2019.00259
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Field
DocType
Volume
Noise reduction,Bayer filter,Data processing,Image sensor,Pattern recognition,Computer science,Unification,Image denoising,RGB color model,Artificial intelligence,Real image
Journal
abs/1904.12945
ISSN
Citations 
PageRank 
2160-7508
2
0.36
References 
Authors
0
11
Name
Order
Citations
PageRank
Jiaming Liu1132.67
chihao wu2344.51
yuzhi wang3111.16
Qin Xu420.36
Yuqian Zhou5345.93
Haibin Huang617212.21
Chuan Wang711013.58
Shaofan Cai820.36
Yifan Ding9166.97
Haoqiang Fan1022712.94
Jue Wang112871155.89