aalto1 untyped-item.component.html

Sources of Uncertainty in 3D Scene Reconstruction

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

19

Series

Computer Vision – ECCV 2024 Workshops: Milan, Italy, September 29–October 4, 2024, Proceedings, Part XVII, pp. 271-289, Lecture Notes in Computer Science ; Volume 15639

Abstract

The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms to directly address or quantify uncertainties arising from the presence of noise, occlusions, confounding outliers, and imprecise camera pose inputs. In this paper, we introduce a taxonomy that categorizes different sources of uncertainty inherent in these methods. Moreover, we extend NeRF- and GS-based methods with uncertainty estimation techniques, including learning uncertainty outputs and ensembles, and perform an empirical study to assess their ability to capture the sensitivity of the reconstruction. Our study highlights the need for addressing various uncertainty aspects when designing NeRF/GS-based methods for uncertainty-aware 3D reconstruction.

Description

Other note

Citation

Klasson, M, Mereu, R, Kannala, J & Solin, A 2025, Sources of Uncertainty in 3D Scene Reconstruction. in A Del Bue, C Canton, J Pont-Tuset & T Tommasi (eds), Computer Vision – ECCV 2024 Workshops : Milan, Italy, September 29–October 4, 2024, Proceedings, Part XVII. Lecture Notes in Computer Science, vol. 15639, Springer, pp. 271-289, European Conference on Computer Vision, Milano, Italy, 29/09/2024. https://doi.org/10.1007/978-3-031-91585-7_17

Endorsement

Review

Supplemented By

Referenced By