SPaGS: Fast and Accurate 3D Gaussian Splatting for Spherical Panoramas

Simple item page
dc.contributor.authorLi, Junboen_US
dc.contributor.authorHahlbohm, Florianen_US
dc.contributor.authorScholz, Timonen_US
dc.contributor.authorEisemann, Martinen_US
dc.contributor.authorTauscher, Jan-Philippen_US
dc.contributor.authorMagnor, Marcusen_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:54:08Z
dc.date.available2025-06-20T07:54:08Z
dc.date.issued2025
dc.description.abstractIn this paper we propose SPaGS, a high-quality, real-time free-viewpoint rendering approach from 360-degree panoramic images. While existing methods building on Neural Radiance Fields or 3D Gaussian Splatting have difficulties to achieve real-time frame rates and high-quality results at the same time, SPaGS combines the advantages of an explicit 3D Gaussian-based scene representation and ray casting-based rendering to attain fast and accurate results. Central to our new approach is the exact calculation of axis-aligned bounding boxes for spherical images that significantly accelerates omnidirectional ray casting of 3D Gaussians. We also present a new dataset consisting of ten real-world scenes recorded with a drone that incorporates both calibrated 360-degree panoramic images as well as perspective images captured simultaneously, i.e., with the same flight trajectory. Our evaluation on this new dataset as well as established benchmarks demonstrates that SPaGS excels over state-of-the-art methods in terms of both rendering quality and speed.en_US
dc.description.number4
dc.description.sectionheadersGaussians
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70171
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70171
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70171
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 → Rendering; Point-based models; Rasterization; Machine learning approaches
dc.subjectComputing methodologies → Rendering
dc.subjectPoint
dc.subjectbased models
dc.subjectRasterization
dc.subjectMachine learning approaches
dc.titleSPaGS: Fast and Accurate 3D Gaussian Splatting for Spherical Panoramasen_US
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
cgf70171.pdf
Size:
14.71 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1068_mm1.mp4
Size:
47.72 MB
Format:
Video MP4
Download
Thumbnail Image
Name:
paper1068_mm2.pdf
Size:
134.08 KB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 4