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

facebooktwittermailshare

RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL

Abstract: 

Nowadays, three-dimensional (3D) point cloud has been an emerging medium to represent real-world scenes and objects. However, there is a considerable proportion of point clouds whose color attribute information is not captured during the acquisition process due to the device or environment limitations. This poses a great challenge for efficient management and utilization of point clouds. To address this problem, we introduce an automatic colorization scheme based on a deep generative network for 3D point clouds. The proposed approach uses the range images of point could geometry and trains a conditional generative adversarial network to predict the color of those images. Later, the color of each pixel in the colorized image is projected back to its corresponding point in the 3D point cloud. The experimental results demonstrate the efficacy of the proposed colorization approach in facilitating users to recognize and handle 3D point cloud data better.

up
0 users have voted:

Paper Details

Authors:
Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin
Submitted On:
10 September 2019 - 9:10pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Weisi Lin
Paper Code:
2767
Document Year:
2019
Cite

Document Files

icip2019_eposter_jonguk.pdf

(7)

Subscribe

[1] Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin, "RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4576. Accessed: Sep. 15, 2019.
@article{4576-19,
url = {http://sigport.org/4576},
author = {Jong-Uk Hou; Baoquan Zhao; Naushad Ansari; Weisi Lin },
publisher = {IEEE SigPort},
title = {RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL},
year = {2019} }
TY - EJOUR
T1 - RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL
AU - Jong-Uk Hou; Baoquan Zhao; Naushad Ansari; Weisi Lin
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4576
ER -
Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin. (2019). RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL. IEEE SigPort. http://sigport.org/4576
Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin, 2019. RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL. Available at: http://sigport.org/4576.
Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin. (2019). "RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL." Web.
1. Jong-Uk Hou, Baoquan Zhao, Naushad Ansari, Weisi Lin. RANGE IMAGE BASED POINT CLOUD COLORIZATION USING CONDITIONAL GENERATIVE MODEL [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4576