Real-time 3D scene reconstruction from monocular images using SLAM for NeRF with NeRF-SLAM
Real-time 3D scene reconstruction from monocular images using SLAM for NeRF with NeRF-SLAM
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
arXiv paper abstract https://arxiv.org/abs/2210.13641
arXiv PDF paper https://arxiv.org/pdf/2210.13641.pdf
... propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images.
... leverage recent advances in dense monocular SLAM and real-time hierarchical volumetric neural radiance fields.
... 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.
... proposed uncertainty-based depth loss, ... achieve not only good photometric accuracy, but also great geometric accuracy.
... proposed pipeline achieves better geometric and photometric accuracy than competing approaches (up to 179% better PSNR and 86% better L1 depth), while working in real-time and using only monocular images.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Opmerkingen