TY - GEN
T1 - FiveNet
T2 - IS and T International Symposium on Electronic Imaging: Computational Imaging
AU - Ponomarenko, Mykola
AU - Marchuk, Vladimir
AU - Egiazarian, Karen
N1 - Funding Information:
Vladimir Marchuk would like to acknowledge the financial support of the Russian Federation represented by the Ministry of Science and Higher Education of the Russian Federation (Agreement No. 075-15-2021-997 of 09/28/2021), and Mykola Ponomarenko - the financial support of Huawei-Tampere University project 3114100158, FlexISP.
Publisher Copyright:
© 2022, Society for Imaging Science and Technology.
jufoid=84313
PY - 2022
Y1 - 2022
N2 - In this paper, a convolutional neural network for joint image demosaicing, denoising, deblurring, super-resolution and clarity enhancement is proposed. The network inputs are four-channel Bayer CFA image (R, G, G, B) and three channels of the same size containing distortions maps, namely, noise level map, blur level map, and clarity degradation map. It is shown that the designed network FiveNet can effectively process images with the mix of five different distortions. It is also demonstrated that adding clarity enhancement into the processing chain can additionally increase image quality (by up to 3-4 dB in PSNR). A small dataset ClarityDegr120 of color images with different clarity degradations and enhancements is designed using images processed by FiveNet. Mean opinion scores (MOS) for the test set are collected. The MOS prove that clarity enhancement can significantly increase image visual quality. A comparative analysis using the MOS demonstrates a low correspondence between image quality metrics and human perception for the clarity enhancement task.
AB - In this paper, a convolutional neural network for joint image demosaicing, denoising, deblurring, super-resolution and clarity enhancement is proposed. The network inputs are four-channel Bayer CFA image (R, G, G, B) and three channels of the same size containing distortions maps, namely, noise level map, blur level map, and clarity degradation map. It is shown that the designed network FiveNet can effectively process images with the mix of five different distortions. It is also demonstrated that adding clarity enhancement into the processing chain can additionally increase image quality (by up to 3-4 dB in PSNR). A small dataset ClarityDegr120 of color images with different clarity degradations and enhancements is designed using images processed by FiveNet. Mean opinion scores (MOS) for the test set are collected. The MOS prove that clarity enhancement can significantly increase image visual quality. A comparative analysis using the MOS demonstrates a low correspondence between image quality metrics and human perception for the clarity enhancement task.
U2 - 10.2352/EI.2022.34.14.COIMG-218
DO - 10.2352/EI.2022.34.14.COIMG-218
M3 - Conference contribution
AN - SCOPUS:85132397327
VL - 34
T3 - IS and T International Symposium on Electronic Imaging Science and Technology
BT - Proc. IS&T Int’l. Symp. on Electronic Imaging: Computational Imaging, 2022
Y2 - 17 January 2022 through 26 January 2022
ER -