Continuous Markov Random Fields for Robust Stereo Estimation thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Continuous Markov Random Fields for Robust Stereo Estimation

Published on Nov 12, 20125292 Views

In this paper we present a novel slanted-plane model which reasons jointly about occlusion boundaries as well as depth. We formulate the problem as one of inference in a hybrid MRF composed of both co

Related categories

Chapter list

Continuous Markov Random Fields for Robust Stereo Estimation00:00
Goal00:05
Related Work01:14
Our Approach02:24
Our model02:56
Energy Function (1)04:00
Energy Function (2)04:17
Energy Function (3)04:44
Energy Function (4)05:38
Energy Function (5)06:09
Inference / Learning06:51
Experiments07:37
Evaluation - Middlebury08:17
Result Example - Middlebury (1)08:39
Result Example - Middlebury (2)08:59
Evaluation - KITTI09:06
Result Examples - KITTI09:44
Training Set Size09:50
Importance of Energy Terms10:22
Conclusion11:27