We present vMAP, an object-level dense SLAM system using neural field representations. Each object is represented by a small MLP, enabling efficient, watertight object modelling without the need for 3D priors. As an RGB-D camera browses a scene with no prior information, vMAP detects object instances on-the-fly, and dynamically adds them to its map. Specifically, thanks to the power of vectorised training, vMAP can optimise as many as 50 individual objects in a single scene, with an extremely efficient training speed of 5Hz map update. We experimentally demonstrate significantly improved scene-level and object-level reconstruction quality compared to prior neural field SLAM systems. Project page: https://kxhit.github.io/vMAP.
@article{arxiv.2302.01838,
title = {vMAP: Vectorised Object Mapping for Neural Field SLAM},
author = {Xin Kong and Shikun Liu and Marwan Taher and Andrew J. Davison},
journal= {arXiv preprint arXiv:2302.01838},
year = {2023}
}