From Cluster to Desktop: A Cache-Accelerated INR framework for Interactive Visualization of Tera-Scale Data

Simple item page
dc.contributor.authorZavorotny, Danielen_US
dc.contributor.authorWu, Qien_US
dc.contributor.authorBauer, Daviden_US
dc.contributor.authorMa, Kwan-Liuen_US
dc.contributor.editorReina, Guidoen_US
dc.contributor.editorRizzi, Silvioen_US
dc.contributor.editorGueunet, Charlesen_US
dc.date.accessioned2025-05-26T07:15:11Z
dc.date.available2025-05-26T07:15:11Z
dc.date.issued2025
dc.description.abstractMachine learning has enabled the use of implicit neural representations (INRs) to efficiently compress and reconstruct massive scientific datasets. However, despite advances in fast INR rendering algorithms, INR-based rendering remains computationally expensive, as computing data values from an INR is significantly slower than reading them from GPU memory. This bottleneck currently restricts interactive INR visualization to professional workstations. To address this challenge, we introduce an INR rendering framework accelerated by a scalable, multi-resolution GPU cache capable of efficiently representing tera-scale datasets. By minimizing redundant data queries and prioritizing novel volume regions, our method reduces the number of INR computations per frame, achieving an average 5× speedup over the state-of-the-art INR rendering method while still maintaining high visualization quality. Coupled with existing hardware-accelerated INR compressors, our framework enables scientists to generate and compress massive datasets in situ on high-performance computing platforms and then interactively explore them on consumer-grade hardware post hoc.en_US
dc.description.sectionheadersPapers
dc.description.seriesinformationEurographics Symposium on Parallel Graphics and Visualization
dc.identifier.doi10.2312/pgv.20251153
dc.identifier.isbn978-3-03868-274-5
dc.identifier.issn1727-348X
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/pgv.20251153
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pgv20251153
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → 3D imaging; Ray tracing; Volumetric models
dc.subjectComputing methodologies → 3D imaging
dc.subjectRay tracing
dc.subjectVolumetric models
dc.titleFrom Cluster to Desktop: A Cache-Accelerated INR framework for Interactive Visualization of Tera-Scale Dataen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pgv20251153.pdf
Size:
8.07 MB
Format:
Adobe Portable Document Format
Download
Collections
EGPGV25: Eurographics Symposium on Parallel Graphics and Visualization