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{Zhi:2022:10.1109/iccv48922.2021.01554,
author = {Zhi, S and Laidlow, T and Leutenegger, S and Davison, AJ},
doi = {10.1109/iccv48922.2021.01554},
publisher = {IEEE},
title = {In-place scene labelling and understanding with implicit scene representation},
url = {http://dx.doi.org/10.1109/iccv48922.2021.01554},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties.We extend neural radiance fields (NeRF) to jointly encode semantics with appearance and geometry, so that complete and accurate 2D semantic labels can be achieved using a small amount of in-place annotations specific to the scene. The intrinsic multi-view consistency and smoothness of NeRF benefit semantics by enabling sparse labels to efficiently propagate. We show the benefit of this approach when labels are either sparse or very noisy in room-scale scenes. We demonstrate its advantageous properties in various interesting applications such as an efficient scene labelling tool, novel semantic view synthesis, label denoising, super-resolution, label interpolation and multi-view semantic label fusion in visual semantic mapping systems.
AU  - Zhi,S
AU  - Laidlow,T
AU  - Leutenegger,S
AU  - Davison,AJ
DO  - 10.1109/iccv48922.2021.01554
PB  - IEEE
PY  - 2022///
TI  - In-place scene labelling and understanding with implicit scene representation
UR  - http://dx.doi.org/10.1109/iccv48922.2021.01554
UR  - https://ieeexplore.ieee.org/document/9710936
UR  - http://hdl.handle.net/10044/1/97142
ER  -
Download