The Community for Technology Leaders
Green Image
Issue No. 06 - June (2009 vol. 31)
ISSN: 0162-8828
pp: 974-988
Tien-Tsin Wong , The Chinese University of Hong Kong, Hong Kong
Hujun Bao , Zhejiang University, Hangzhou
Jiaya Jia , The Chinese University of Hong Kong, Hong Kong
Guofeng Zhang , Zhejiang University, Hangzhou
This paper presents a novel method for recovering consistent depth maps from a video sequence. We propose a bundle optimization framework to address the major difficulties in stereo reconstruction, such as dealing with image noise, occlusions, and outliers. Different from the typical multi-view stereo methods, our approach not only imposes the photo-consistency constraint, but also explicitly associates the geometric coherence with multiple frames in a statistical way. It thus can naturally maintain the temporal coherence of the recovered dense depth maps without over-smoothing. To make the inference tractable, we introduce an iterative optimization scheme by first initializing the disparity maps using a segmentation prior and then refining the disparities by means of bundle optimization. Instead of defining the visibility parameters, our method implicitly models the reconstruction noise as well as the probabilistic visibility. After bundle optimization, we introduce an efficient space-time fusion algorithm to further reduce the reconstruction noise. Our automatic depth recovery is evaluated using a variety of challenging video examples.
Stereo, Motion, Depth cues
Tien-Tsin Wong, Hujun Bao, Jiaya Jia, Guofeng Zhang, "Consistent Depth Maps Recovery from a Video Sequence", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. , pp. 974-988, June 2009, doi:10.1109/TPAMI.2009.52
97 ms
(Ver 3.1 (10032016))