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{Handa:2016:10.1007/978-3-319-49409-8_9,
author = {Handa, A and Bloesch, M and Patraucean, V and Stent, S and McCormac, J and Davison, A},
doi = {10.1007/978-3-319-49409-8_9},
pages = {67--82},
publisher = {Springer Verlag},
title = {gvnn: neural network library for geometric computer vision},
url = {http://dx.doi.org/10.1007/978-3-319-49409-8_9},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - We introduce gvnn, a neural network library in Torch aimed towards bridging the gap between classic geometric computer vision and deep learning. Inspired by the recent success of Spatial Transformer Networks, we propose several new layers which are often used as parametric transformations on the data in geometric computer vision. These layers can be inserted within a neural network much in the spirit of the original spatial transformers and allow backpropagation to enable end-to-end learning of a network involving any domain knowledge in geometric computer vision. This opens up applications in learning invariance to 3D geometric transformation for place recognition, end-to-end visual odometry, depth estimation and unsupervised learning through warping with a parametric transformation for image reconstruction error.
AU  - Handa,A
AU  - Bloesch,M
AU  - Patraucean,V
AU  - Stent,S
AU  - McCormac,J
AU  - Davison,A
DO  - 10.1007/978-3-319-49409-8_9
EP  - 82
PB  - Springer Verlag
PY  - 2016///
SN  - 0302-9743
SP  - 67
TI  - gvnn: neural network library for geometric computer vision
UR  - http://dx.doi.org/10.1007/978-3-319-49409-8_9
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000389501100009&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - http://hdl.handle.net/10044/1/43656
ER  -
Download