Human beings process stereoscopic correspondence across multiple scales. However, this bio-inspiration is ignored by state-of-the-art cost aggregation methods for dense stereo correspondence. In this paper, a generic cross-scale cost aggregation framework is proposed to allow multi-scale interaction in cost aggregation. We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels. Then, an inter-scale regularizer is introduced into optimization and solving this new optimization problem leads to the proposed framework. Since the regularization term is independent of the similarity kernel, various cost aggregation methods can be integrated into the proposed general framework. We show that the cross-scale framework is important as it effectively and efficiently expands state-of-the-art cost aggregation methods and leads to significant improvements, when evaluated on Middlebury, KITTI and New Tsukuba datasets.
|Title of host publication||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Publisher||IEEE Computer Society|
|Number of pages||8|
|ISBN (Electronic)||9781479951178, 9781479951178|
|State||Published - 24 Sep 2014|
|Event||27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014 - Columbus, United States|
Duration: 23 Jun 2014 → 28 Jun 2014
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Conference||27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014|
|Period||23/06/14 → 28/06/14|
Bibliographical notePublisher Copyright:
© 2014 IEEE.
- cost aggregation
- stereo matching