Neural Intersection Function

Simple item page
dc.contributor.authorFujieda, Shinen_US
dc.contributor.authorKao, Chih Chenen_US
dc.contributor.authorHarada, Takahiroen_US
dc.contributor.editorBikker, Jaccoen_US
dc.contributor.editorGribble, Christiaanen_US
dc.date.accessioned2023-06-25T09:06:57Z
dc.date.available2023-06-25T09:06:57Z
dc.date.issued2023
dc.description.abstractThe ray casting operation in the Monte Carlo ray tracing algorithm usually adopts a bounding volume hierarchy (BVH) to accelerate the process of finding intersections to evaluate visibility. However, its characteristics are irregular, with divergence in memory access and branch execution, so it cannot achieve maximum efficiency on GPUs. This paper proposes a novel Neural Intersection Function based on a multilayer perceptron whose core operation contains only dense matrix multiplication with predictable memory access. Our method is the first solution integrating the neural network-based approach and BVH-based ray tracing pipeline into one unified rendering framework. We can evaluate the visibility and occlusion of secondary rays without traversing the most irregular and time-consuming part of the BVH and thus accelerate ray casting. The experiments show the proposed method can reduce the secondary ray casting time for direct illumination by up to 35% compared to a BVH-based implementation and still preserve the image quality.en_US
dc.description.sectionheadersDeep Learning for Graphics
dc.description.seriesinformationHigh-Performance Graphics - Symposium Papers
dc.identifier.doi10.2312/hpg.20231135
dc.identifier.isbn978-3-03868-229-5
dc.identifier.issn2079-8687
dc.identifier.pages43-53
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.2312/hpg.20231135
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/hpg20231135
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 -> Neural networks; Ray tracing
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectRay tracing
dc.titleNeural Intersection Functionen_US
Files
Original bundle
Now showing 1 - 3 of 3
No Thumbnail Available
Name:
043-053.pdf
Size:
92.28 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
mm1010.pdf
Size:
73.49 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
mm1010.pdf
Size:
73.49 MB
Format:
Adobe Portable Document Format
Download
Collections
High-Performance Graphics 2023 - Symposium Papers