view article
Figure 7
Normalized backward and forward attention scores of the EDVR-STF model to predict continuous target HR frames in Case 1 and Case 2. For both cases, the LR frame separation was set to one and the HR image sequence was down-sampled by a factor of 20. No Poisson noise was generated for the testing data.

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 32| Part 2| March 2025| Pages 432-441
https://doi.org/10.1107/S1600577525000323
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS