Disparity map quality for image-based rendering based on multiple metrics

Author

Vandewalle, Patrick ; Varekamp, Chris

Author_Institution

Philips Group Innovation - Res., Eindhoven, Netherlands

fYear

2014

fDate

9-10 Dec. 2014

Firstpage

1

Lastpage

5

Abstract

While a wide range of disparity estimation algorithms exists, only few methods are available to analyze the quality of a disparity map. We present a new two-dimensional approach to disparity map evaluation using the stereo matching error and the temporal error. These measures give a good indication of stereo or multi-view performance on a 3D display. Results are illustrated on a ground truth disparity map with multiple distortions as well as on a commercially available disparity estimator using varying post-processing settings on a real stereoscopic video sequence.

Keywords

image matching; rendering (computer graphics); stereo image processing; 3D display; disparity estimation algorithms; disparity map evaluation; disparity map quality; distortions; ground truth disparity map; image-based rendering; multiple metrics; multiview performance; stereo matching error; stereoscopic video sequence; temporal error; two-dimensional approach; Estimation; Image analysis; Noise measurement; Stereo image processing; Three-dimensional displays; Video sequences; depth map; disparity map quality; image quality;

fLanguage

English

Publisher

ieee

Conference_Titel

3D Imaging (IC3D), 2014 International Conference on

Conference_Location

Liege

Type

conf

DOI

10.1109/IC3D.2014.7032599

Filename

7032599