TY - CHAP
T1 - 3DRRDB
T2 - Super Resolution of Multiple Remote Sensing Images using 3D Residual in Residual Dense Blocks
AU - Ibrahim, Mohamed Ramzy
AU - Benavente, Robert
AU - Lumbreras, Felipe
AU - Ponsa, Daniel
N1 - Funding Information:
This work has been supported by the Spanish Ministry of Science and Innovation under project BOSSS TIN2017-89723-P.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - The rapid advancement of Deep Convolutional Neural Networks helped in solving many remote sensing problems, especially the problems of super-resolution. However, most state-of-the-art methods focus more on Single Image Super-Resolution neglecting Multi-Image Super-Resolution. In this work, a new proposed 3D Residual in Residual Dense Blocks model (3DRRDB) focuses on remote sensing Multi-Image Super-Resolution for two different single spectral bands. The proposed 3DRRDB model explores the idea of 3D convolution layers in deeply connected Dense Blocks and the effect of local and global residual connections with residual scaling in Multi-Image Super-Resolution. The model tested on the Proba-V challenge dataset shows a significant improvement above the current state-of-the-art models scoring a Corrected Peak Signal to Noise Ratio (cPSNR) of 48.79 dB and 50.83 dB for Near Infrared (NIR) and RED Bands respectively. Moreover, the proposed 3DRRDB model scores a Corrected Structural Similarity Index Measure (cSSIM) of 0.9865 and 0.9909
AB - The rapid advancement of Deep Convolutional Neural Networks helped in solving many remote sensing problems, especially the problems of super-resolution. However, most state-of-the-art methods focus more on Single Image Super-Resolution neglecting Multi-Image Super-Resolution. In this work, a new proposed 3D Residual in Residual Dense Blocks model (3DRRDB) focuses on remote sensing Multi-Image Super-Resolution for two different single spectral bands. The proposed 3DRRDB model explores the idea of 3D convolution layers in deeply connected Dense Blocks and the effect of local and global residual connections with residual scaling in Multi-Image Super-Resolution. The model tested on the Proba-V challenge dataset shows a significant improvement above the current state-of-the-art models scoring a Corrected Peak Signal to Noise Ratio (cPSNR) of 48.79 dB and 50.83 dB for Near Infrared (NIR) and RED Bands respectively. Moreover, the proposed 3DRRDB model scores a Corrected Structural Similarity Index Measure (cSSIM) of 0.9865 and 0.9909
UR - http://www.scopus.com/inward/record.url?scp=85137769064&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/06c3861a-7a31-3273-8f0c-5addfc2f5960/
U2 - 10.1109/CVPRW56347.2022.00047
DO - 10.1109/CVPRW56347.2022.00047
M3 - Chapter
AN - SCOPUS:85137769064
SN - 9781665487399
T3 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
SP - 322
EP - 331
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
ER -