Distributed Neural Representation for Reactive in situ Visualization

Qi Wu, Joseph A. Insley, Victor A. Mateevitsi, Silvio Rizzi, and Kwan-Liu Ma

IEEE Symposium on Large Data Analysis and Visualization (LDAV) Poster, 2022

Figure 1: The training and evaluation setup described in this poster. As a proof of concept, we use a regular volume that is pre-partitioned into two. Ghost voxels are also computed during the partitioning process.

Abstract

Volumetric grids have recently been used by many recent works for representing complex scenes implicitly. A volumetric neural representation can be several orders of magnitude smaller in size while still preserving most of high-frequency details. However, most volumes used in large-scale in situ visualization and analysis are partitioned and generated directly in parallel. Therefore, a compatible technique to create volumetric neural representations for these situations is much needed. In this project, we explore the possibility of constructing and optimizing such a representation for large-scale distributed volumes. We present our preliminary results in this poster. We also outline our plans to integrate our techniques with existing in situ visualization and analysis pipelines.

BibTex

@inproceedings{9966405,
    author={Wu, Qi and Insley, Joseph A. and Mateevitsi, Victor A. and Rizzi, Silvio and Ma, Kwan-Liu},
    booktitle={2022 IEEE 12th Symposium on Large Data Analysis and Visualization (LDAV)}, 
    title={Distributed Volumetric Neural Representation for in situ Visualization and Analysis}, 
    year={2022},
    volume={},
    number={},
    pages={1-2},
    doi={10.1109/LDAV57265.2022.9966405}
}