vMAP: Vectorised Object Mapping for Neural Field SLAM

被引:36
作者
Kong, Xin [1 ]
Liu, Shikun [1 ]
Taher, Marwan [1 ]
Davison, Andrew J. [1 ]
机构
[1] Imperial Coll London, Dyson Robot Lab, London, England
来源
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR | 2023年
基金
英国工程与自然科学研究理事会;
关键词
D O I
10.1109/CVPR52729.2023.00098
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:952 / 961
页数:10
相关论文
共 48 条
[11]  
Kong Xin, 2020, P IEEE RSJ C INT ROB
[12]  
Li Guanglin, 2022, C ROB LEARN CORL
[13]  
Liu Shikun, 2019, P IEEE C COMP VIS PA
[14]  
Lyu Xiaoyang, 2021, P NAT C ART INT AAAI
[15]  
Majercik Alexander, 2018, J COMPUTER GRAPHICS
[16]  
McCormac John, 2018, P INT C 3D VIS 3DV
[17]   Occupancy Networks: Learning 3D Reconstruction in Function Space [J].
Mescheder, Lars ;
Oechsle, Michael ;
Niemeyer, Michael ;
Nowozin, Sebastian ;
Geiger, Andreas .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :4455-4465
[18]  
Mildenhall Ben, 2020, P EUR C COMP VIS ECC
[19]  
Ming Yuhang, 2022, P INT S MIX AUGM REA
[20]   Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels [J].
Misra, Ishan ;
Zitnick, C. Lawrence ;
Mitchell, Margaret ;
Girshick, Ross .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2930-2939