LEARNING RAWIMAGE DENOISING USING A PARAMETRIC COLOR IMAGE MODEL

被引:0
作者
Achddou, Raphael [1 ]
Gousseau, Yann [1 ]
Ladjal, Said [1 ]
机构
[1] Inst Polytech Paris, LTCI, Telecom Paris, Paris, France
来源
2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2023年
关键词
image denoising; color modeling; synthetic learning; INFORMATION; STATISTICS;
D O I
10.1109/ICIP49359.2023.10222629
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning methods for image restoration have produced impressive results over recent years. Nevertheless, they generalize poorly and need large learning image datasets to be collected for each new acquisition modality. In order to avoid the building of such datasets, it has been recently proposed to develop synthetic image datasets for training image restoration methods, using scale invariant dead leaves models. While the geometry of such models can be successfully encoded with only a few parameters, the color content cannot be straightforwardly encoded. In this paper, we leverage the concept of color lines prior to build a light parametric color model relying on a chromaticity/luminance factorization. Further, we show that the corresponding synthetic dataset can be used to train neural networks for the denoising of RAW images from different camera-phones, without using any image from these devices. This shows the potential of our approach to increase the generalization capacity of learning-based denoising approaches in real case scenarios.
引用
收藏
页码:2690 / 2694
页数:5
相关论文
共 50 条
[31]   A Review of Image Denoising With Deep Learning [J].
Yapici, Ahmet ;
Akcayol, M. Ali .
2ND INTERNATIONAL INFORMATICS AND SOFTWARE ENGINEERING CONFERENCE (IISEC), 2021,
[32]   A Triple Deep Image Prior Model for Image Denoising Based on Mixed Priors and Noise Learning [J].
Hu, Yong ;
Xu, Shaoping ;
Cheng, Xiaohui ;
Zhou, Changfei ;
Hu, Yufeng .
APPLIED SCIENCES-BASEL, 2023, 13 (09)
[33]   Infrared star image denoising using regions with deep reinforcement learning [J].
Zhang, Zhenduo ;
Zheng, Wenbo ;
Ma, Zhanjun ;
Yin, Limei ;
Xie, Ming ;
Wu, Yuanhao .
INFRARED PHYSICS & TECHNOLOGY, 2021, 117 (117)
[34]   A Modified Artificial Bee Colony Algorithm for Image Denoising Using Parametric Wavelet Thresholding Method [J].
Zhang X. .
Pattern Recognition and Image Analysis, 2018, 28 (03) :557-568
[35]   Image Denoising Based on Non-parametric ADMM Algorithm [J].
Ye, Xinchen ;
Zhang, Mingliang ;
Yan, Qianyu ;
Fan, Xin ;
Luo, Zhongxuan .
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2018, PT II, 2018, 11165 :318-328
[36]   Single Image Denoising via a New Lightweight Learning-Based Model [J].
Rezvani, Sadjad ;
Soleymani Siahkar, Fatemeh ;
Rezvani, Yasin ;
Alavi Gharahbagh, Abdorreza ;
Abolghasemi, Vahid .
IEEE ACCESS, 2024, 12 :121077-121092
[37]   Medical image denoising using convolutional denoising autoencoders [J].
Gondara, Lovedeep .
2016 IEEE 16TH INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2016, :241-246
[38]   On Prediction of Image Denoising Expedience Using Neural Networks [J].
Rubel, Andrii ;
Rubel, Oleksii ;
Lukin, Vladimir .
2018 INTERNATIONAL SCIENTIFIC-PRACTICAL CONFERENCE: PROBLEMS OF INFOCOMMUNICATIONS SCIENCE AND TECHNOLOGY (PIC S&T), 2018, :629-634
[39]   Image Denoising Using Superpixel-Based PCA [J].
Malladi, Sree Ramya S. P. ;
Ram, Sundaresh ;
Rodriguez, Jeffrey J. .
IEEE TRANSACTIONS ON MULTIMEDIA, 2021, 23 :2297-2309
[40]   CT Image Denoising Model Using Image Segmentation for Image Quality Enhancement for Liver Tumor Detection Using CNN [J].
Gavini, Venkateswarlu ;
Lakshmi, Gurusamy Ramasamy Jothi .
TRAITEMENT DU SIGNAL, 2022, 39 (05) :1807-1814