TY - GEN
T1 - Inverted Residual Fourier Transformation for Lightweight Single Image Deblurring
AU - Yae, Shunsuke
AU - Ikehara, Masaaki
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In recent years, encoder-decoder structures are widely used for single image deblurring and successfully restore high quality images. How-ever, FLOPs and the number of parameters tend to increase to restore a high-quality image. Thus, we propose a new lightweight network (IRFTNet) based on DeepRFT. This network has two features to improve performance and lightweight. First, a new backbone called Inverted Residual Fourier Transformation block (IRFTblock) based on inverted residual block is introduced to decrease computational complexity. Second, a new module called Lower Feature Synthesis (LFS) was introduced to efficiently transfer encoder information from lower layers to upper layers. These improvements resulted in a 32.98dB in PSNR on the GoPro dataset, despite approximately half FLOPs and the number of parameters of DeepRFT.
AB - In recent years, encoder-decoder structures are widely used for single image deblurring and successfully restore high quality images. How-ever, FLOPs and the number of parameters tend to increase to restore a high-quality image. Thus, we propose a new lightweight network (IRFTNet) based on DeepRFT. This network has two features to improve performance and lightweight. First, a new backbone called Inverted Residual Fourier Transformation block (IRFTblock) based on inverted residual block is introduced to decrease computational complexity. Second, a new module called Lower Feature Synthesis (LFS) was introduced to efficiently transfer encoder information from lower layers to upper layers. These improvements resulted in a 32.98dB in PSNR on the GoPro dataset, despite approximately half FLOPs and the number of parameters of DeepRFT.
KW - Fast fourier transform
KW - Lightweight
KW - Single image deblurring
UR - http://www.scopus.com/inward/record.url?scp=85149141737&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149141737&partnerID=8YFLogxK
U2 - 10.1109/ICCE56470.2023.10043510
DO - 10.1109/ICCE56470.2023.10043510
M3 - Conference contribution
AN - SCOPUS:85149141737
T3 - Digest of Technical Papers - IEEE International Conference on Consumer Electronics
BT - 2023 IEEE International Conference on Consumer Electronics, ICCE 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Y2 - 6 January 2023 through 8 January 2023
ER -