TY - GEN
T1 - Difference of Convolution for Deep Compressive Sensing
AU - Canh, Thuong Nguyen
AU - Jeon, Byeungwoo
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Deep learning-based compressive sensing (DCS) has improved the single scale compressive sensing (CS) with fast and high reconstruction quality. Researchers have further extended it to multi-scale DCS which improves reconstruction quality based on Wavelet decomposition. In this work, we mimic the Difference of Gaussian via convolution and propose a scheme named as Difference of Convolution-based multi-scale DCS (DoC-DCS). Unlike the multi-scale DCS based on a well-designed filter in the wavelet domain, our DoC-DCS jointly learns decomposition, sampling, and reconstruction thereby outperforms other state-of-the-art deep learning based CS methods.
AB - Deep learning-based compressive sensing (DCS) has improved the single scale compressive sensing (CS) with fast and high reconstruction quality. Researchers have further extended it to multi-scale DCS which improves reconstruction quality based on Wavelet decomposition. In this work, we mimic the Difference of Gaussian via convolution and propose a scheme named as Difference of Convolution-based multi-scale DCS (DoC-DCS). Unlike the multi-scale DCS based on a well-designed filter in the wavelet domain, our DoC-DCS jointly learns decomposition, sampling, and reconstruction thereby outperforms other state-of-the-art deep learning based CS methods.
KW - compressive sensing
KW - deep learning
KW - difference of convolution
KW - difference of Gaussian
UR - https://www.scopus.com/pages/publications/85076805255
U2 - 10.1109/ICIP.2019.8803165
DO - 10.1109/ICIP.2019.8803165
M3 - Conference contribution
AN - SCOPUS:85076805255
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2105
EP - 2109
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - IEEE Computer Society
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
Y2 - 22 September 2019 through 25 September 2019
ER -