As-Rigid-As-Possible Stereo under Second Order Smoothness Priors
- Cite this paper as:
- Zhang C., Li Z., Cai R., Chao H., Rui Y. (2014) As-Rigid-As-Possible Stereo under Second Order Smoothness Priors. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8690. Springer, Cham
Imposing smoothness priors is a key idea of the top-ranked global stereo models. Recent progresses demonstrated the power of second order priors which are usually defined by either explicitly considering three-pixel neighborhoods, or implicitly using a so-called 3D-label for each pixel. In contrast to the traditional first-order priors which only prefer fronto-parallel surfaces, second-order priors encourage arbitrary collinear structures. However, we still can find defective regions in matching results even under such powerful priors, e.g., large textureless regions. One reason is that most of the stereo models are non-convex, where pixel-wise smoothness priors, i.e., local constraints, are too flexible to prevent the solution from trapping in bad local minimums. On the other hand, long-range spatial constraints, especially the segment-based priors, have advantages on this problem. However, segment-based priors are too rigid to handle curved surfaces. We present a mixture model to combine the benefits of these two kinds of priors, whose energy function consists of two terms 1) a Laplacian operator on the disparity map which imposes pixel-wise second-order smoothness; 2) a segment-wise matching cost as a function of quadratic surface, which encourages “as-rigid-as-possible” smoothness. To effectively solve the problem, we introduce an intermediate term to decouple the two subenergies, which enables an alternated optimization algorithm that is about an order of magnitude faster than PatchMatch . Our approach is one of the top ranked models on the Middlebury benchmark at sub-pixel accuracy.
Unable to display preview. Download preview PDF.