Imperial College London
Alternate

ProfessorAndrewDavison

Faculty of Engineering, Department of Computing

Professor of Robot Vision
 
 
 
//

Contact

 

+44 (0)20 7594 8316a.davison Website

 
 
//

Assistant

 

Ms Lucy Atthis +44 (0)20 7594 8259

 
//

Location

 

303William Penney LaboratorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Mazur:2023:10.1109/icra48891.2023.10160800,
author = {Mazur, K and Sucar, E and Davison, AJ},
doi = {10.1109/icra48891.2023.10160800},
pages = {8201--8207},
publisher = {IEEE},
title = {Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding},
url = {http://dx.doi.org/10.1109/icra48891.2023.10160800},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which fuses general learned features from a standard pre-trained network into a highly efficient 3D geometric neural field representation during real-time SLAM. The fused 3D feature maps inherit the coherence of the neural field's geometry representation. This means that tiny amounts of human labelling interacting at runtime enable objects or even parts of objects to be robustly and accurately segmented in an open set manner. Project page: https://makezur.github.io/FeatureRealisticFusion/
AU  - Mazur,K
AU  - Sucar,E
AU  - Davison,AJ
DO  - 10.1109/icra48891.2023.10160800
EP  - 8207
PB  - IEEE
PY  - 2023///
SP  - 8201
TI  - Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding
UR  - http://dx.doi.org/10.1109/icra48891.2023.10160800
ER  -
Download