Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION

Abstract: 

Point cloud are precise digital record of an objects in space. It starts to getting more attention due to the additional information it provides compared to 2D images. In this paper, we propose a new deep learning architecture called R-CovNets, designed for 3D object recognition. Unlike to previous approaches that usually sample or convert point cloud into three-dimensional grids, R-CovNets does not reckon on any preprocessing. Our architecture is specially designed for cloud point, permutation invariant and can take as input, a data of any size. In our experiments with a series of well-known benchmarks, R-CovNets achieves state-of-art performances.

up
0 users have voted:

Paper Details

Authors:
Danielle Tchuinkou Kwadj and Christophe Bobda
Submitted On:
8 October 2018 - 2:07pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Christophe Bobda
Paper Code:
ICIP18001
Document Year:
2018
Cite

Document Files

R-COVNET.pdf

(8 downloads)

Subscribe

[1] Danielle Tchuinkou Kwadj and Christophe Bobda, "R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3638. Accessed: Oct. 17, 2018.
@article{3638-18,
url = {http://sigport.org/3638},
author = {Danielle Tchuinkou Kwadj and Christophe Bobda },
publisher = {IEEE SigPort},
title = {R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION},
year = {2018} }
TY - EJOUR
T1 - R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION
AU - Danielle Tchuinkou Kwadj and Christophe Bobda
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3638
ER -
Danielle Tchuinkou Kwadj and Christophe Bobda. (2018). R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION. IEEE SigPort. http://sigport.org/3638
Danielle Tchuinkou Kwadj and Christophe Bobda, 2018. R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION. Available at: http://sigport.org/3638.
Danielle Tchuinkou Kwadj and Christophe Bobda. (2018). "R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION." Web.
1. Danielle Tchuinkou Kwadj and Christophe Bobda. R-COVNET: RECURRENT NEURAL CONVOLUTION NETWORK FOR 3D OBJECT RECOGNITION [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3638