STSRNet: Deep Joint Space–Time Super-Resolution for Vector Field Visualization



Yifei An, Han-Wei Shen, Guihua Shan, Guan Li, Jun Liu

 View presentation:2022-10-20T21:21:00ZGMT-0600Change your timezone on the schedule page
2022-10-20T21:21:00Z

Exemplar figure, described by caption below — In this paper, we proposed a joint space-time super-resolution deep learning-based model to reconstruct high temporal and spatial resolution vector field sequences. The model consists of a temporal super-resolution model and a spatial super-resolution, using a physically based loss function combined with temporal coherence for reconstructing vectors. We proved the effectiveness of our model on different datasets through quantitative and qualitative evaluations.

Prerecorded Talk

The live footage of the talk, including the Q&A, can be viewed on the session page, Visualization Teaching and Literacy (cont.) and Machine Learning for Vis..

Fast forward

Abstract