Multiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fields

Simple item page
dc.contributor.authorKim, Jungeonen_US
dc.contributor.authorPark, Geonsooen_US
dc.contributor.authorLee, Seungyongen_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:55:25Z
dc.date.available2025-06-20T07:55:25Z
dc.date.issued2025
dc.description.abstractRecent methods, such as 2D Gaussian Splatting and Gaussian Opacity Fields, have aimed to address the geometric inaccuracies of 3D Gaussian Splatting while retaining its superior rendering quality. However, these approaches still struggle to reconstruct smooth and reliable geometry, particularly in scenes with significant color variation across viewpoints, due to their per-point appearance modeling and single-view optimization constraints. In this paper, we propose an effective multiview geometric regularization strategy that integrates multiview stereo (MVS) depth, RGB, and normal constraints into Gaussian Splatting initialization and optimization. Our key insight is the complementary relationship between MVS-derived depth points and Gaussian Splatting-optimized positions: MVS robustly estimates geometry in regions of high color variation through local patch-based matching and epipolar constraints, whereas Gaussian Splatting provides more reliable and less noisy depth estimates near object boundaries and regions with lower color variation. To leverage this insight, we introduce a median depthbased multiview relative depth loss with uncertainty estimation, effectively integrating MVS depth information into Gaussian Splatting optimization. We also propose an MVS-guided Gaussian Splatting initialization to avoid Gaussians falling into suboptimal positions. Extensive experiments validate that our approach successfully combines these strengths, enhancing both geometric accuracy and rendering quality across diverse indoor and outdoor scenes.en_US
dc.description.number4
dc.description.sectionheadersGaussians
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70179
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70179
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70179
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 → Point-based models
dc.subjectComputing methodologies → Point
dc.subjectbased models
dc.titleMultiview Geometric Regularization of Gaussian Splatting for Accurate Radiance Fieldsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70179.pdf
Size:
5.78 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 4