Uncertainty-Aware Gaussian Splatting with View-Dependent Regularization for High-Fidelity 3D Reconstruction

Simple item page
dc.contributor.authorLiu, Shengjunen_US
dc.contributor.authorWu, Jiangxinen_US
dc.contributor.authorWu, Wenhuien_US
dc.contributor.authorChu, Lixiangen_US
dc.contributor.authorLiu, Xinruen_US
dc.contributor.editorWang, Beibeien_US
dc.contributor.editorWilkie, Alexanderen_US
dc.date.accessioned2025-06-20T07:49:47Z
dc.date.available2025-06-20T07:49:47Z
dc.date.issued2025
dc.description.abstract3D Gaussian Splatting (3DGS) has emerged as a groundbreaking paradigm for explicit scene representation, achieving photorealistic novel view synthesis with real-time rendering capabilities. However, reconstructing geometrically consistent and accurate surfaces under complex real-world scenarios remains a critical challenge. Current 3DGS frameworks primarily rely on photometric loss optimization, which often results in multi-view geometric inconsistencies and inadequate handling of texture-less regions due to two inherent limitations: 1) the absence of explicit geometric constraints during Gaussian parameter optimization, and 2) the lack of effective mechanisms to resolve multi-view geometric ambiguities. To address these challenges, we propose Uncertainty-Aware Gaussian Splatting (UA-GS), a novel framework that integrates geometric priors with view-dependent uncertainty modeling to explicitly capture and resolve multi-view inconsistencies. For efficient optimization of Gaussian attributes, our approach introduces a spherical harmonics-based uncertainty representation that dynamically models view-dependent geometric variations. Building on this framework, we further design uncertainty-aware optimization strategies. Extensive experiments on real-world and synthetic benchmarks demonstrate that our method significantly outperforms state-of-the-art 3DGS-based approaches in geometric accuracy while retaining competitive rendering quality. Code and data will be made available soon.en_US
dc.description.sectionheadersGaussians
dc.description.seriesinformationEurographics Symposium on Rendering
dc.identifier.doi10.2312/sr.20251192
dc.identifier.isbn978-3-03868-292-9
dc.identifier.issn1727-3463
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.2312/sr.20251192
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/sr20251192
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 -> Collision detection; Hardware -> Sensors and actuators; PCB design and layout
dc.subjectComputing methodologies
dc.subjectCollision detection
dc.subjectHardware
dc.subjectSensors and actuators
dc.subjectPCB design and layout
dc.titleUncertainty-Aware Gaussian Splatting with View-Dependent Regularization for High-Fidelity 3D Reconstructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
sr20251192.pdf
Size:
13.19 MB
Format:
Adobe Portable Document Format
Download
Collections
Rendering 2025 - Symposium Track