2026-04-13T19:06:19Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/3650892026-02-04T06:48:05Zcom_2072_1033col_2072_452950

urn:hdl:2117/365089 Stochastic neural radiance fields: quantifying uncertainty in implicit 3D representations Shen, Jianxiong Ruiz Ovejero, Adrià Agudo Martínez, Antonio Moreno-Noguer, Francesc Àrees temàtiques de la UPC::Informàtica::Automàtica i control Neural networks (Computer science) Computational intelligence Neural Radiance Fields Bayesian learning Xarxes neuronals (Informàtica) Intel·ligència computacional © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works Neural Radiance Fields (NeRF) has become a popular framework for learning implicit 3D representations and addressing different tasks such as novel-view synthesis or depth-map estimation. However, in downstream applications where decisions need to be made based on automatic predictions, it is critical to leverage the confidence associated with the model estimations. Whereas uncertainty quantification is a long-standing problem in Machine Learning, it has been largely overlooked in the recent NeRF literature. In this context, we propose Stochastic Neural Radiance Fields (S-NeRF), a generalization of standard NeRF that learns a probability distribution over all the possible radiance fields modeling the scene. This distribution allows to quantify the uncertainty associated with the scene information provided by the model. S-NeRF optimization is posed as a Bayesian learning problem that is efficiently addressed using the Variational Inference framework. Exhaustive experiments over benchmark datasets demonstrate that S-NeRF is able to provide more reliable predictions and confidence values than generic approaches previously proposed for uncertainty estimation in other domains. This work is supported partly by the Chinese Scholarship Council (CSC) under grant (201906120031), by the Spanish government under project MoHuCo PID2020- 120049RB-I00, the ERA-Net Chistera project IPALM PCI2019-103386 and María de Maeztu Seal of Excellence MDM-2016-0656. Adria Ruiz acknowledges financial support from MICINN through the program Juan de la Cierva. Peer Reviewed Postprint (author's final draft) 2021 Conference report https://ieeexplore.ieee.org/document/9665942 info:eu-repo/grantAgreement/MDM/2PE/MDM-2016-0656 info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-096001-B-C32/ES/CONTROL Y GESTION DE ENERGIA EN VEHICULOS ELECTRICOS HIBRIDOS CON PILAS DE COMBUSTIBLE/ info:eu-repo/grantAgreement/MINECO/2PE/201980E101 http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Open Access Attribution-NonCommercial-NoDerivs 3.0 Spain