Data Parallel Ray Tracing of Massive Scenes based on Neural Proxy

dc.contributor.authorXu, Shunkangen_US
dc.contributor.authorXu, Xiangen_US
dc.contributor.authorXu, Yanningen_US
dc.contributor.authorWang, Luen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:54Z
dc.date.available2024-10-13T18:03:54Z
dc.date.issued2024
dc.description.abstractData-parallel ray tracing is an important method for rendering massive scenes that exceed local memory. Nevertheless, its efficacy is markedly contingent upon bandwidth owing to the substantial ray data transfer during the rendering process. In this paper, we advance the utilization of neural representation geometries in data-parallel rendering to reduce ray forwarding and intersection overheads. To this end, we introduce a lightweight geometric neural representation, denoted as a ''neural proxy.'' Utilizing our neural proxies, we propose an efficient data-parallel ray tracing framework that significantly minimizes ray transmission and intersection overheads. Compared to state-of-the-art approaches, our method achieved a 2.29∼ 3.36× speedup with an almost imperceptible image quality loss.en_US
dc.description.sectionheadersRendering and Lighting I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241287
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241287
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241287
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 → Computer graphics; Ray tracing; Neural networks
dc.subjectComputing methodologies → Computer graphics
dc.subjectRay tracing
dc.subjectNeural networks
dc.titleData Parallel Ray Tracing of Massive Scenes based on Neural Proxyen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
pg20241287.pdf
Size:
32.58 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
paper1365_mm.mp4
Size:
68.66 MB
Format:
Video MP4