620 likes | 827 Views
What happened last time?. We have looked at ways for finding a disparity map D that minimizes our energy functionwherem(p,dp) computes color dissimilarity for matching pixel p at disparity dpN denotes all spatial neighbors in 4-connectivitys() is the smoothness function. We use the Potts mode
E N D
1. Smoothness Term Michael Bleyer
LVA Stereo Vision
2. What happened last time? We have looked at ways for finding a disparity map D that minimizes our energy function where m(p,dp) computes color dissimilarity for matching pixel p at disparity dp N denotes all spatial neighbors in 4-connectivity s() is the smoothness function. We use the Potts model: We have learned about move making graph-cut algorithms: a swaps a expansions fusion-moves