Quality Analysis of Virtual Views on Stereoscopic Video Content

By Mattias Eisenbarth, Florian Seitner, and Margrit Gelautz

Abstract

Depth Image-Based Rendering (DIBR) allows the creation of virtual camera viewpoints from a 2D image and its corresponding disparity map. This enables a variety of new applications in 3D film post-production where disparities can be computed in an automatic way from the stereoscopic content. Examples include scene depth correction, content remastering and multi-view generation for auto-stereoscopic displays. In this paper, a comparison of state-of-the-art DIBR techniques in the context of 3D video adaptation is presented. We first provide an evaluation method that enables subjective comparison of the visual quality of DIBRgenerated 3D film sequences. Based on this, we then evaluate the impact of image artifacts on the visual comfort and the depth impression for four different DIBR approaches.

Reference

M. Eisenbarth, F. Seitner, M. Gelautz: "Quality Analysis of Virtual Views on Stereoscopic Video Content"; Talk: International Conference on Systems, Signals and Image Processing, Vienna; 04-11-2012 - 04-13-2012; in: "Proceedings of 9th International Conference on Systems, Signals and Image Processings (IWSSIP 2012)", (2012), ISBN: 978-3-200-02588-2; 333 - 336.

BibTeX

@inproceedings{TUW-210978, author = {Eisenbarth, Mattias and Seitner, Florian and Gelautz, Margrit}, title = {Quality Analysis of Virtual Views on Stereoscopic Video Content}, booktitle = {Proceedings of 9th International Conference on Systems, Signals and Image Processings (IWSSIP 2012)}, year = {2012}, pages = {333--336}, url = {http://publik.tuwien.ac.at/files/PubDat_210978.pdf}, isbn = {978-3-200-02588-2}, keywords = {DIBR, evaluation, warping, in-filling}, note = {talk: International Conference on Systems, Signals and Image Processing, Vienna; 2012-04-11 -- 2012-04-13} } Click into the text area and press Ctrl+A/Ctrl+C or ⌘+A/⌘+C to copy the BibTeX into your clipboard… or download the BibTeX.