Continuous Markov Random Fields for Robust Stereo Estimation

Details Continuous Markov Random Fields for Robust Stereo Estimation Continuous Markov Random Fields for Robust Stereo Estimation

2012-04-06

arxiv.org/abs/1204.1393v1

Computer Science

Computer Vision and Pattern Recognition

Scientific paper

In this paper we present a novel slanted-plane MRF model which reasons jointly about occlusion boundaries as well as depth. We formulate the problem as the one of inference in a hybrid MRF composed of both continuous (i.e., slanted 3D planes) and discrete (i.e., occlusion boundaries) random variables. This allows us to define potentials encoding the ownership of the pixels that compose the boundary between segments, as well as potentials encoding which junctions are physically possible. Our approach outperforms the state-of-the-art on Middlebury high resolution imagery as well as in the more challenging KITTI dataset, while being more efficient than existing slanted plane MRF-based methods, taking on average 2 minutes to perform inference on high resolution imagery.

Affiliated with

Also associated with

No associations

Rating

Continuous Markov Random Fields for Robust Stereo Estimation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Continuous Markov Random Fields for Robust Stereo Estimation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Continuous Markov Random Fields for Robust Stereo Estimation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-183071