DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization



Chaoli Wang, Jun Han

 View presentation:2022-10-20T14:12:00ZGMT-0600Change your timezone on the schedule page
2022-10-20T14:12:00Z

Exemplar figure, described by caption below — Selected visualization results generated from the authors' DL4SciVis works. From left to right: reconstruction of vector field data from representative streamlines (CG&A 2019), learning surface representation via a graph convolutional network (SurfNet, EuroVis 2022), generating super-resolution for vector field data (SSR-VFD, PacificVis 2020), and clustering and selecting stream surfaces via an autoencoder (FlowNet, TVCG 2020).

Prerecorded Talk

The live footage of the talk, including the Q&A, can be viewed on the session page, ML for VIS.

Fast forward

Keywords

Scientific visualization, deep learning, survey

Abstract

Since 2016, we have witnessed the tremendous growth of artificial intelligence+visualization (AI+VIS) research. However, existing survey papers on AI+VIS focus on visual analytics and information visualization, not scientific visualization (SciVis). In this paper, we survey related deep learning (DL) works in SciVis, specifically in the direction of DL4SciVis: designing DL solutions for solving SciVis problems. To stay focused, we primarily consider works that handle scalar and vector field data but exclude mesh data. We classify and discuss these works along six dimensions: domain setting, research task, learning type, network architecture, loss function, and evaluation metric. The paper concludes with a discussion of the remaining gaps to fill along the discussed dimensions and the grand challenges we need to tackle as a community. This state-of-the-art survey guides SciVis researchers in gaining an overview of this emerging topic and points out future directions to grow this research.