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

facebooktwittermailshare

SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES

Abstract: 

Depth prediction from a single monocular image is a challenging yet valuable task, as often a depth sensor is not available. The state-of-the-art approach \cite{Liu2016} combines a deep fully convolutional network (DFCN) with a conditional random field (CRF), allowing the CRF to correct and smooth the depth values estimated by the DFCN according to efficient contextual modeling.
However, using the output of the DFCN as unary input for CRF is limited by using only the last layer of the DFCN. The middle layers of the DFCN have been shown to carry useful information for other scene understanding tasks, which may help to improve the prediction quality.
This paper proposes a novel super-column super-pixel (SCSP) feature that is the combination of multiple layers of the DFCN after a super-pixel pooling process. The proposed approach based on the SCSP features reduces the root mean square (rms) error of the prediction by more than 16\% in NYUv2 dataset.

up
0 users have voted:

Paper Details

Authors:
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan
Submitted On:
15 September 2017 - 9:27pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Xufeng Guo
Paper Code:
3442
Document Year:
2017
Cite

Document Files

poster-

(202)

Subscribe

[1] Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan, "SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2165. Accessed: Nov. 19, 2019.
@article{2165-17,
url = {http://sigport.org/2165},
author = {Xufeng Guo; Kien Nguyen; Simon Denman; Clinton Fookes; Sridha Sridharan },
publisher = {IEEE SigPort},
title = {SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES},
year = {2017} }
TY - EJOUR
T1 - SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES
AU - Xufeng Guo; Kien Nguyen; Simon Denman; Clinton Fookes; Sridha Sridharan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2165
ER -
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. (2017). SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES. IEEE SigPort. http://sigport.org/2165
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan, 2017. SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES. Available at: http://sigport.org/2165.
Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. (2017). "SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES." Web.
1. Xufeng Guo, Kien Nguyen, Simon Denman, Clinton Fookes, Sridha Sridharan. SINGLE IMAGE DEPTH PREDICTION USING SUPER-COLUMN SUPER-PIXEL FEATURES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2165