NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
Name
2210.13641.pdf
Size
12.94 MB
Format
Adobe PDF
Checksum (MD5)
a432e5582e57a15dc148c954f6607cb6
Author(s)
Rosinol, Antoni
Leonard, John J.
Carlone, Luca
Date Issued
October 1, 2023
Journal
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Publisher
IEEE
Citation
Rosinol, Antoni, Leonard, John J. and Carlone, Luca. 2023. "NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields." 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Version
Author's final manuscript
Abstract
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from casually taken monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time hierarchical volumetric neural radiance fields. Our insight is that dense monocular SLAM provides the right information to fit a neural radiance field of the scene in real-time, by providing accurate pose estimates and depth-maps with associated uncertainty. Our proposed pipeline achieves better geometric and photometric accuracy than competing approaches (up to 178% better PSNR and 75% better L1 depth), while working in real-time and using only monocular images.
Description
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) October 1-5, 2023. Detroit, USA
MIT Department
Massachusetts Institute of Technology. Department of Mechanical Engineering
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/iros55552.2023.10341922
