Saved in:
Bibliographic Details
Main Authors: Skorokhodov, Vsevolod, Drozdova, Darya, Yudin, Dmitry
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.08012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914830298906624
author Skorokhodov, Vsevolod
Drozdova, Darya
Yudin, Dmitry
author_facet Skorokhodov, Vsevolod
Drozdova, Darya
Yudin, Dmitry
contents Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such methods is their inability to assess the confidence of the model in its predictions. In this paper, we propose a new neural network model for the formation of extended vector representations, called uSF, which allows the model to predict not only color and semantic label of each point, but also estimate the corresponding values of uncertainty. We show that with a small number of images available for training, a model quantifying uncertainty performs better than a model without such functionality. Code of the uSF approach is publicly available at https://github.com/sevashasla/usf/.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08012
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle uSF: Learning Neural Semantic Field with Uncertainty
Skorokhodov, Vsevolod
Drozdova, Darya
Yudin, Dmitry
Computer Vision and Pattern Recognition
Artificial Intelligence
Recently, there has been an increased interest in NeRF methods which reconstruct differentiable representation of three-dimensional scenes. One of the main limitations of such methods is their inability to assess the confidence of the model in its predictions. In this paper, we propose a new neural network model for the formation of extended vector representations, called uSF, which allows the model to predict not only color and semantic label of each point, but also estimate the corresponding values of uncertainty. We show that with a small number of images available for training, a model quantifying uncertainty performs better than a model without such functionality. Code of the uSF approach is publicly available at https://github.com/sevashasla/usf/.
title uSF: Learning Neural Semantic Field with Uncertainty
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2312.08012