TY - GEN
T1 - High-Resolution Projection Network combining High-Resolution Optical Flow Compensation for Video Super-Resolution
AU - Sun, Yifei
AU - Chen, Zhengxia
AU - Jin, Yuying
AU - Feng, Xiaoyi
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - The Super-Resolution (SR) task is to generate high-resolution (HR) images/videos using low-resolution (LR) ones. At present, the Single Image Super-Resolution (SISR) methods have achieved superior performance. However, Video Super-Resolution (VSR) methods still have some disadvantages such as edge blurring, high-frequency details missing and motion artifacts. This paper proposes an end-To-end HR feature projection VSR network HOF-HRPN, which consists of a High-Resolution Optical Flow (HOF) and a High-Resolution Projection Network (HRPN). The HOF network estimates the HR optical flow and compensates it to the neighboring frames to achieve accurate frame alignment. The HRPN is composed of a multi frame feature projection channel and a single frame SR channel in parallel. HRPN takes into account the advantages that single frame SR and VSR can extract missing high-frequency details from intra-frame and inter-frame, respectively. It fuses high-frequency details obtained from multi-scale LR projection learning and single frame SR results. A large number of comparative experiments based on public datasets verify that HOF-HRPN is robust and can recover accurate pixel values, clear edges and rich textures.
AB - The Super-Resolution (SR) task is to generate high-resolution (HR) images/videos using low-resolution (LR) ones. At present, the Single Image Super-Resolution (SISR) methods have achieved superior performance. However, Video Super-Resolution (VSR) methods still have some disadvantages such as edge blurring, high-frequency details missing and motion artifacts. This paper proposes an end-To-end HR feature projection VSR network HOF-HRPN, which consists of a High-Resolution Optical Flow (HOF) and a High-Resolution Projection Network (HRPN). The HOF network estimates the HR optical flow and compensates it to the neighboring frames to achieve accurate frame alignment. The HRPN is composed of a multi frame feature projection channel and a single frame SR channel in parallel. HRPN takes into account the advantages that single frame SR and VSR can extract missing high-frequency details from intra-frame and inter-frame, respectively. It fuses high-frequency details obtained from multi-scale LR projection learning and single frame SR results. A large number of comparative experiments based on public datasets verify that HOF-HRPN is robust and can recover accurate pixel values, clear edges and rich textures.
KW - feature projection and fusion
KW - optical flow estimation and compensation
KW - single image super-resolution
KW - temporal-spatial feature
KW - video super-resolution
UR - http://www.scopus.com/inward/record.url?scp=85199484308&partnerID=8YFLogxK
U2 - 10.1109/ICIPMC62364.2024.10586677
DO - 10.1109/ICIPMC62364.2024.10586677
M3 - 会议稿件
AN - SCOPUS:85199484308
T3 - 2024 3rd International Conference on Image Processing and Media Computing, ICIPMC 2024
SP - 234
EP - 238
BT - 2024 3rd International Conference on Image Processing and Media Computing, ICIPMC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Image Processing and Media Computing, ICIPMC 2024
Y2 - 17 May 2024 through 19 May 2024
ER -