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

facebooktwittermailshare

FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction

Abstract: 

Shearlet Transform (ST) is one of the most effective methods for Densely-Sampled Light Field (DSLF) reconstruction from a Sparsely-Sampled Light Field (SSLF). However, ST requires a precise disparity estimation of the SSLF. To this end, in this paper a state-of-the-art optical flow method, i.e. PWC-Net, is employed to estimate bidirectional disparity maps between neighboring views in the SSLF. Moreover, to take full advantage of optical flow and ST for DSLF reconstruction, a novel learning-based method, referred to as Flow-Assisted Shearlet Transform (FAST), is proposed in this paper. Specifically, FAST consists of two deep convolutional neural networks, i.e. disparity refinement network and view synthesis network, which fully leverage the disparity information to synthesize novel views via warping and blending and to improve the novel view synthesis performance of ST. Experimental results demonstrate the superiority of the proposed FAST method over the other state-of-the-art DSLF reconstruction methods on nine challenging real-world SSLF sub-datasets with large disparity ranges (up to 26 pixels).

up
0 users have voted:

Paper Details

Authors:
Reinhard Koch, Robert Bregovic, Atanas Gotchev
Submitted On:
16 September 2019 - 12:24pm
Short Link:
Type:
Presentation Slides
Event:
Paper Code:
WP.L5.2
Document Year:
2019
Cite

Document Files

ICIP2019_FAST.pdf

(14)

Subscribe

[1] Reinhard Koch, Robert Bregovic, Atanas Gotchev , "FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4643. Accessed: Nov. 20, 2019.
@article{4643-19,
url = {http://sigport.org/4643},
author = {Reinhard Koch; Robert Bregovic; Atanas Gotchev },
publisher = {IEEE SigPort},
title = {FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction},
year = {2019} }
TY - EJOUR
T1 - FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction
AU - Reinhard Koch; Robert Bregovic; Atanas Gotchev
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4643
ER -
Reinhard Koch, Robert Bregovic, Atanas Gotchev . (2019). FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction. IEEE SigPort. http://sigport.org/4643
Reinhard Koch, Robert Bregovic, Atanas Gotchev , 2019. FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction. Available at: http://sigport.org/4643.
Reinhard Koch, Robert Bregovic, Atanas Gotchev . (2019). "FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction." Web.
1. Reinhard Koch, Robert Bregovic, Atanas Gotchev . FAST: Flow-Assisted Shearlet Transform for Densely-sampled Light Field Reconstruction [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4643