1. Introduction

Conferences: IEEE Transactions on Visualization and Computer Graphics ( Early Access )
Author: Chaoli Wang, Jun Han
Year: 2022
ISBNs, DOls, PMIDs, or arXiv IDs： 10.1109/TVCG.2022.3167896
Cite: C. Wang and J. Han, “DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization,” in IEEE Transactions on Visualization and Computer Graphics, doi: 10.1109/TVCG.2022.3167896.
Reportor: 孙百乐
Attachment: pdf

2. Figures

image.png

3. Summary

这是一篇调研在科学可视化中应用深度学习的工作的Survey，选取了来自可视化和图形学领域的六个期刊（IEEE TVCG, CGF, IEEE CG&A, C&G, JoV, VI），三个会议（VIS, EuroVis, PacificVis）的59篇paper，从Domain settings、Research tasks、Learning type、Network architecture、Loss function、Evaluation metric六个维度分析这些文章，并提出了开放性的问题和挑战。

4. Main Points

  1. 科学可视化与CV和CG领域相似，很多问题可以借鉴
  2. Deeplearning + SciVis 可以有很多玩法，详情请见research tasks

DL4SciVis.pdf