← Search

Marcelo Walter

2 accepted papers

2019

On the Performance of DIBR Methods When Using Depth Maps from State-of-the-art Stereo Matching Algorithms

ICASSP 2019accepted

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…

Cited by 0SourceScholar
2015

Selective hole-filling for depth-image based rendering

ICASSP 2015accepted

One of the biggest challenges in view interpolation is to fill the regions without projective information in the synthesized view. In this paper, we present a new approach that identifies and corrects different types of missing information. In the first stage, we propose a fast solution to tackle th…

Cited by 0SourceScholar