OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS

Simple item page
dc.contributor.authorLi, Haiyi
dc.contributor.authorChen, Qi
dc.contributor.authorKalkofen, Denis
dc.contributor.authorChen, Hsiang-Ting
dc.contributor.editorMasia, Belen
dc.contributor.editorThies, Justus
dc.date.accessioned2026-04-17T12:15:39Z
dc.date.available2026-04-17T12:15:39Z
dc.date.issued2026
dc.description.abstractRecent advances in 3D Gaussian Splatting (3DGS) have achieved state-of-the-art results for novel view synthesis. However, efficiently capturing high-fidelity reconstructions of specific objects within complex scenes remains a significant challenge. A key limitation of existing active reconstruction methods is their reliance on scene-level uncertainty metrics, which are often biased by irrelevant background clutter and lead to inefficient view selection for object-centric tasks. We present OUGS, a novel framework that addresses this challenge with a more principled, physically-grounded uncertainty formulation for 3DGS. Our core innovation is to derive uncertainty directly from the explicit physical parameters of the 3D Gaussian primitives (e.g., position, scale, rotation). By propagating the covariance of these parameters through the rendering Jacobian, we establish a highly interpretable uncertainty model. This foundation allows us to seamlessly integrate semantic segmentation masks to produce a targeted, object-aware uncertainty score that effectively disentangles the object from its environment. This enables a more effective active view selection strategy that prioritizes views critical to improving object fidelity. Experimental evaluations on public datasets demonstrate that our approach significantly improves the efficiency of the 3DGS reconstruction process and achieves higher quality for targeted objects compared to existing state-of-the-art methods, while also serving as a robust uncertainty estimator for the global scene.
dc.description.number2
dc.description.sectionheadersAdvancing 3D Gaussian Splatting
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume45
dc.identifier.doi10.1111/cgf.70363
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70363
dc.identifier.urihttps://doi.org/10.1111/cgf.70363
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies → Reconstruction
dc.subjectActive vision
dc.subjectImage-based rendering
dc.subject3D reconstruction
dc.subjectShape analysis
dc.subject3D Gaussian Splatting
dc.subjectCCS Concepts
dc.titleOUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70363.pdf
Size:
17.58 MB
Format:
Adobe Portable Document Format
Download
Collections
45-Issue 2
EG 2026 - Full Papers - CGF 45-Issue 2