TY - GEN
T1 - Video super-resolution using wave-shape network
AU - Wu, Yanan
AU - Kamata, Sei Ichiro
N1 - Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/12/20
Y1 - 2019/12/20
N2 - Video super-resolution (VSR) aims to restore a high-resolution (HR) image from multiple low-resolution (LR) frames. Previous works deal with inputs LR frames by stacking or warping and only use single scale features for reconstruction. Most of them didn't consider fusing multi-scale spatial and inter-frame temporal information, which may result in loss of details. In this paper, a novel architecture named Wave-shape network is proposed, which is designed to treat each frame as a separate source of information and fuse different temporal frames through a multi-scale structure. This fusion strategy enables us to capture more complete structure and context information for HR image quality improvement. We evaluate this model on Vid4 dataset and the results show Waveshape network not only achieves significant improvement in vision but also obtains much higher PSNR and SSIM than most previous VSR methods.
AB - Video super-resolution (VSR) aims to restore a high-resolution (HR) image from multiple low-resolution (LR) frames. Previous works deal with inputs LR frames by stacking or warping and only use single scale features for reconstruction. Most of them didn't consider fusing multi-scale spatial and inter-frame temporal information, which may result in loss of details. In this paper, a novel architecture named Wave-shape network is proposed, which is designed to treat each frame as a separate source of information and fuse different temporal frames through a multi-scale structure. This fusion strategy enables us to capture more complete structure and context information for HR image quality improvement. We evaluate this model on Vid4 dataset and the results show Waveshape network not only achieves significant improvement in vision but also obtains much higher PSNR and SSIM than most previous VSR methods.
KW - Convolution neural network
KW - Multi-scale feature fusion
KW - Video super-resolution
KW - Wave-shape network
UR - http://www.scopus.com/inward/record.url?scp=85081176952&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081176952&partnerID=8YFLogxK
U2 - 10.1145/3376067.3376079
DO - 10.1145/3376067.3376079
M3 - Conference contribution
AN - SCOPUS:85081176952
T3 - ACM International Conference Proceeding Series
SP - 132
EP - 136
BT - Proceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019
PB - Association for Computing Machinery
T2 - 3rd International Conference on Video and Image Processing, ICVIP 2019
Y2 - 20 December 2019 through 23 December 2019
ER -