Bayesian uncertainty analysis for underwater 3D reconstruction with neural radiance fields

Haojie Lian, Xinhao Li, Yilin Qu, Jing Du, Zhuxuan Meng, Jie Liu, Leilei Chen

科研成果: 期刊稿件文章同行评审

13 引用 (Scopus)

摘要

Neural radiance fields (NeRFs) are a deep learning technique that generates novel views of 3D scenes from multi-view images. As an extension of NeRFs, SeaThru-NeRF mitigates the effects of scattering media on the structural appearance and geometric information. However, like most deep learning models, SeaThru-NeRF has inherent uncertainty in its predictions and produces artifacts in the rendering results, which limits its practical deployment in underwater unmanned autonomous navigation. To address this issue, we introduce a spatial perturbation field based on Bayes' rays into SeaThru-NeRF and perform Laplace approximation to obtain Gaussian distribution of the parameters, so that the uncertainty at each spatial location can be evaluated. Additionally, because artifacts inherently correspond to regions of high uncertainty, we remove them by thresholding based on our uncertainty field. Numerical experiments are provided to demonstrate the effectiveness of this approach.

源语言英语
文章编号115806
期刊Applied Mathematical Modelling
138
DOI
出版状态已出版 - 2月 2025

指纹

探究 'Bayesian uncertainty analysis for underwater 3D reconstruction with neural radiance fields' 的科研主题。它们共同构成独一无二的指纹。

引用此