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

Wang, Chaoli; Han, Jianda

doi:10.1109/tvcg.2022.3167896

Cited by 24 publications

(8 citation statements)

References 135 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As our method is primarily related to scene representation networks, we review related literature covering SRN architectures and training, examining applications in the computer vision and sci-vis domains. Our work is part of a larger domain of research called DL4SciVis, for which Wang and Han provide a comprehensive survey [29].…”

Section: Related Workmentioning

confidence: 99%

Deep Hierarchical Super Resolution for Scientific Data

Wurster

Guo

Shen

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Scene representation networks (SRNs) have been recently proposed for compression and visualization of scientific data. However, state-of-the-art SRNs do not adapt the allocation of available network parameters to the complex features found in scientific data, leading to a loss in reconstruction quality. We address this shortcoming with an adaptively placed multi-grid SRN (APMGSRN) and propose a domain decomposition training and inference technique for accelerated parallel training on multi-GPU systems. We also release an open-source neural volume rendering application that allows plug-and-play rendering with any PyTorch-based SRN. Our proposed APMGSRN architecture uses multiple spatially adaptive feature grids that learn where to be placed within the domain to dynamically allocate more neural network resources where error is high in the volume, improving state-of-the-art reconstruction accuracy of SRNs for scientific data without requiring expensive octree refining, pruning, and traversal like previous adaptive models. In our domain decomposition approach for representing large-scale data, we train an set of APMGSRNs in parallel on separate bricks of the volume to reduce training time while avoiding overhead necessary for an out-of-core solution for volumes too large to fit in GPU memory. After training, the lightweight SRNs are used for realtime neural volume rendering in our open-source renderer, where arbitrary view angles and transfer functions can be explored. A copy of this paper, all code, all models used in our experiments, and all supplemental materials and videos are available at https://github.com/skywolf829/APMGSRN.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Hierarchical Super Resolution for Scientific Data

Wurster

Guo

Shen

et al. 2023

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…A number of tools seek to simplify the process, using either visual interfaces [ MC21 ], or, more recently, natural language [ SLJL10 , MS23 , DBSSD23 , WCA23 ] interfaces, which allow users to produce visualizations by simply typing or speaking their questions or requests. Recent surveys [ WCWQ22 , WWS * 22 , WH22 ] have explored how machine learning is being applied to the data visualization process. Our work builds on these by looking forward and focusing on generative tasks.…”

Section: Background and Related Workmentioning

confidence: 99%

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

Schetinger

Bartolomeo

El‐Assady³

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Because this is a fast‐growing field and many new developments are on the way, we convey the reader to the survey of Wang and Han [WHss] on deep learning‐based approaches for scientific visualization for extensive coverage.…”

Section: Compressed and Neural Representationsmentioning

confidence: 99%

“…The use of neural networks in sci‐vis is a relatively new field. A detailed survey was recently presented by Wang et al [WHss], so here we only briefly describe basic concepts and pointers to papers presenting recent developments.…”

Section: Introductionmentioning

confidence: 99%

State‐of‐the‐art in Large‐Scale Volume Visualization Beyond Structured Data

Sarton,

Zellmann,

Demirci

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Volume data these days is usually massive in terms of its topology, multiple fields, or temporal component. With the gap between compute and memory performance widening, the memory subsystem becomes the primary bottleneck for scientific volume visualization. Simple, structured, regular representations are often infeasible because the buses and interconnects involved need to accommodate the data required for interactive rendering. In this state‐of‐the‐art report, we review works focusing on large‐scale volume rendering beyond those typical structured and regular grid representations. We focus primarily on hierarchical and adaptive mesh refinement representations, unstructured meshes, and compressed representations that gained recent popularity. We review works that approach this kind of data using strategies such as out‐of‐core rendering, massive parallelism, and other strategies to cope with the sheer size of the ever‐increasing volume of data produced by today's supercomputers and acquisition devices. We emphasize the data management side of large‐scale volume rendering systems and also include a review of tools that support the various volume data types discussed.

show abstract

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

Cited by 24 publications

References 135 publications

Deep Hierarchical Super Resolution for Scientific Data

Deep Hierarchical Super Resolution for Scientific Data

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

State‐of‐the‐art in Large‐Scale Volume Visualization Beyond Structured Data

Contact Info

Product

Resources

About