A SIMPLE AND EFFICIENT WAY TO COMPUTE DEPTH MAPS FOR MULTI-VIEW VIDEOS

This paper deals with depth maps extraction from multi-view vi-deo. Contrary to standard stereo matching-based approaches, de-pth maps are computed here using optical flow estimations be-tween consecutive views. We compare our approach with the one proposed in the Depth Estimation Reference Software (DERS) for normalization purposes in the ISO-MPEG 3DV group. Ex-periments conducted on sequences provided to the normalization community show that the presented method provides high quality depth maps in terms of depth fidelity and virtual views synthesis. Moreover, being implemented on the GPU, it is far faster than the DERS