TY - GEN
T1 - Low-Complexity Neural Network Design for Super-Resolution Imaging
AU - Chen, Wei Ting
AU - Liao, Shao Chieh
AU - Chen, Pei Yin
AU - Shih, Hsin Yu
N1 - Funding Information:
This work was supported in part by the Ministry of Science and Technology, Taiwan, under Grant MOST 109-2622-8-006 -018 -TA, and in part by Qualcomm through a Taiwan University Research Collaboration Project.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/9/28
Y1 - 2020/9/28
N2 - Super-resolution imaging is a widely used technology in consumer electronics, such as 4K TV and portable media players. The convolution neural network (CNN) has confirmed the high quality for super-resolution (SR) imaging. However, in order to pursue better imaging quality and higher PSNR/SSIM, recent researches usually involve high complexity architecture and lead to a large amount of memory usage. To overcome these drawbacks, we propose a low-complexity neural network architecture, which has a significant reduction in resource consumption. Furthermore, it also can serve 2X, 3X, and 4X SR images at the same time with a single architecture. Compared with similar less complicated architectures [1]-[2], the results show that our architecture can achieve the best imaging quality (PSNR and SSIM) with the lowest parameter usage.
AB - Super-resolution imaging is a widely used technology in consumer electronics, such as 4K TV and portable media players. The convolution neural network (CNN) has confirmed the high quality for super-resolution (SR) imaging. However, in order to pursue better imaging quality and higher PSNR/SSIM, recent researches usually involve high complexity architecture and lead to a large amount of memory usage. To overcome these drawbacks, we propose a low-complexity neural network architecture, which has a significant reduction in resource consumption. Furthermore, it also can serve 2X, 3X, and 4X SR images at the same time with a single architecture. Compared with similar less complicated architectures [1]-[2], the results show that our architecture can achieve the best imaging quality (PSNR and SSIM) with the lowest parameter usage.
UR - http://www.scopus.com/inward/record.url?scp=85098459714&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098459714&partnerID=8YFLogxK
U2 - 10.1109/ICCE-Taiwan49838.2020.9258128
DO - 10.1109/ICCE-Taiwan49838.2020.9258128
M3 - Conference contribution
AN - SCOPUS:85098459714
T3 - 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
BT - 2020 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
Y2 - 28 September 2020 through 30 September 2020
ER -