2020/01/01 by Xinyi Ying, Longguang Wang, Yingqian Wang +3 · 2 citations
Computer Science · #Advanced Image Processing Techniques #Advanced Vision and Imaging #Image and Signal Denoising Methods
paper · doi:10.1109/lsp.2020.3013518
crossref issued 2020/01/01 · crossref published 2020/01/01 · crossref published-print 2020/01/01 · openalex publication_date 2020/01/01 · crossref created 2020/07/31 · crossref deposited 2022/04/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28 · crossref indexed 2026/07/30
The spatio-temporal information among video sequences is significant for video super-resolution (SR). However, the spatio-temporal information cannot be fully used by existing video SR methods since spatial feature extraction and temporal motion compensation are usually performed sequentially. In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR. Specifically, we introduce deformable 3D convolution (D3D) to integrate deformable convolution with 3D convolution, obtaining both superior spatio-temporal modeling capability and motion-aware modeling flexibility. Extensive experiments have demonstrated the effectiveness of D3D in exploiting spatio-temporal information. Comparative results show that our network achieves state-of-the-art SR performance. Code is available at: https://github.com/XinyiYing/D3Dnet.