Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency

dc.contributor.authorHahlbohm, Florianen_US
dc.contributor.authorFriederichs, Fabianen_US
dc.contributor.authorWeyrich, Timen_US
dc.contributor.authorFranke, Linusen_US
dc.contributor.authorKappel, Moritzen_US
dc.contributor.authorCastillo, Susanaen_US
dc.contributor.authorStamminger, Marcen_US
dc.contributor.authorEisemann, Martinen_US
dc.contributor.authorMagnor, Marcusen_US
dc.contributor.editorBousseau, Adrienen_US
dc.contributor.editorDay, Angelaen_US
dc.date.accessioned2025-05-09T09:10:04Z
dc.date.available2025-05-09T09:10:04Z
dc.date.issued2025
dc.description.abstract3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.en_US
dc.description.number2
dc.description.sectionheadersSplat-tacular Radiance Fields
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70014
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70014
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70014
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution-NonCommercial 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc/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.titleEfficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparencyen_US
Files
Original bundle
Now showing 1 - 4 of 4
No Thumbnail Available
Name:
cgf70014.pdf
Size:
13.34 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
perspective_correct_rendering_comparisons.mp4
Size:
48.59 MB
Format:
Video MP4
Loading...
Thumbnail Image
Name:
supplemental.pdf
Size:
242.59 KB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
view_consistent_rendering_comparisons.mp4
Size:
43.01 MB
Format:
Video MP4