Store and Fetch Immediately: Everything Is All You Need for Space-Time Video Super-resolution


  • Mengshun Hu School of Computer Science, Wuhan University
  • Kui Jiang Huawei Technologies, Cloud BU
  • Zhixiang Nie School of Computer Science, Wuhan University
  • Jiahuan Zhou Wangxuan Institute of Computer Technology, Peking University
  • Zheng Wang School of Computer Science, Wuhan University



CV: Computational Photography, Image & Video Synthesis


Existing space-time video super-resolution (ST-VSR) methods fail to achieve high-quality reconstruction since they fail to fully explore the spatial-temporal correlations, long-range components in particular. Although the recurrent structure for ST-VSR adopts bidirectional propagation to aggregate information from the entire video, collecting the temporal information between the past and future via one-stage representations inevitably loses the long-range relations. To alleviate the limitation, this paper proposes an immediate storeand-fetch network to promote long-range correlation learning, where the stored information from the past and future can be refetched to help the representation of the current frame. Specifically, the proposed network consists of two modules: a backward recurrent module (BRM) and a forward recurrent module (FRM). The former first performs backward inference from future to past, while storing future super-resolution (SR) information for each frame. Following that, the latter performs forward inference from past to future to super-resolve all frames, while storing past SR information for each frame. Since FRM inherits SR information from BRM, therefore, spatial and temporal information from the entire video sequence is immediately stored and fetched, which allows drastic improvement for ST-VSR. Extensive experiments both on ST-VSR and space video super-resolution (S-VSR) as well as time video super-resolution (T-VSR) have demonstrated the effectiveness of our proposed method over other state-of-the-art methods on public datasets. Code is available




How to Cite

Hu, M., Jiang, K., Nie, Z., Zhou, J., & Wang, Z. (2023). Store and Fetch Immediately: Everything Is All You Need for Space-Time Video Super-resolution. Proceedings of the AAAI Conference on Artificial Intelligence, 37(1), 863-871.



AAAI Technical Track on Computer Vision I