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

ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS

Citation Author(s):
Adriano Quilião de Oliveira, Thiago Lopes Trugillo da Silveira, Marcelo Walter, Cláudio Rosito Jung
Submitted by:
Adriano de Oliveira
Last updated:
13 May 2019 - 9:19pm
Document Type:
Poster
Document Year:
2019
Event:
Presenters Name:
de Oliveira, Adriano Q.
Paper Code:
3107

Abstract 

Abstract: 

In this paper we compare the quality of synthesized views produced by four DIBR methods when fed by depth maps estimated by five state-of-the-art stereo matching algorithms. Also, we compute the correlation between four popular metrics for ranking stereo matching algorithms and two metrics commonly used to evaluate synthesized views (PSNR and SSIM) plus one specific for DIBR. Among our findings, we highlight that (i) PSNR and SSIM have a weak correlation with common stereo matching metrics, (ii) using ground-truth depth does not lead necessarily to the best DIBR result; and (iii) estimated depth maps present artifacts that affect differently DIBR methods.

up
0 users have voted:

Dataset Files

ON THE PERFORMANCE OF DIBR METHODS WHEN USING DEPTH MAPS FROM STATE-OF-THE-ART STEREO MATCHING ALGORITHMS

(158)