Abstract: We will present one new method to tackle the challenge of enhancing low-resolution and low frame rate videos into high-resolution slow-motion versions, a process traditionally handled by separate video frame interpolation and super-resolution steps. For a better understanding, we explain two techniques underlying the framework: Deformable Convolutional Networks and Bidirectional Deformable ConvLSTM.

Who: Adam Novozámský

When: 10:00 a.m. Friday, April 5  

Where: The session will occur physically at the Institute of Information Theory and Automation (UTIA). Depending on the number of listeners in room 25 or 45 (café). For directions to the institute, please refer to the following link: https://www.utia.cas.cz/contacts#way

Language: Czech (if you require English, please let us know in advance)

Zoom: https://cesnet.zoom.us/j/95065281700

References: X. Xiang, Y. Tian, Y. Zhang, Y. Fu, J. P. Allebach and C. Xu, "Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution," 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 3367-3376, doi: 10.1109/CVPR42600.2020.00343.