Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?

Simple item page
dc.contributor.authorCelarek, Adamen_US
dc.contributor.authorKopanas, Georgiosen_US
dc.contributor.authorDrettakis, Georgeen_US
dc.contributor.authorWimmer, Michaelen_US
dc.contributor.authorKerbl, Bernharden_US
dc.contributor.editorBousseau, Adrienen_US
dc.contributor.editorDay, Angelaen_US
dc.date.accessioned2025-05-09T09:11:59Z
dc.date.available2025-05-09T09:11:59Z
dc.date.issued2025
dc.description.abstractSince its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real-time novel-view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray-marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in-depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.en_US
dc.description.number2
dc.description.sectionheadersSplat-tacular Radiance Fields
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70032
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70032
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70032
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies->Image-based rendering; Volumetric models; Rasterization; Ray tracing
dc.subjectComputing methodologies
dc.subjectImage
dc.subjectbased rendering
dc.subjectVolumetric models
dc.subjectRasterization
dc.subjectRay tracing
dc.titleDoes 3D Gaussian Splatting Need Accurate Volumetric Rendering?en_US
Files
Original bundle
Now showing 1 - 5 of 5
Thumbnail Image
Name:
cgf70032.pdf
Size:
4.85 MB
Format:
Adobe Portable Document Format
Download
Thumbnail Image
Name:
paper1067_1.pdf
Size:
1.14 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1067_2.pdf
Size:
107.4 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1067_4.mp4
Size:
103.23 MB
Format:
Video MP4
Download
No Thumbnail Available
Name:
renderings.zip
Size:
106.87 MB
Format:
Zip file
Download
Collections
EG 2025 - Full Papers - CGF 44-Issue 2
44-Issue 2