Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer graphics (2nd ed. in C): principles and practice
Computer graphics (2nd ed. in C): principles and practice
A volumetric method for building complex models from range images
SIGGRAPH '96 Proceedings of the 23rd annual conference on Computer graphics and interactive techniques
Theory and Practice of Projective Rectification
International Journal of Computer Vision
A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms
International Journal of Computer Vision
A Cooperative Algorithm for Stereo Matching and Occlusion Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structure from Planar Motions with Small Baselines
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
A Stereo Machine for Video-Rate Dense Depth Mapping and Its New Applications
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Advances in Computational Stereo
IEEE Transactions on Pattern Analysis and Machine Intelligence
Sampling the Disparity Space Image
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Median Filtering in Constant Time
IEEE Transactions on Image Processing
Hi-index | 0.01 |
We present an efficient method that computes dense stereo correspondences by stochastically sampling match quality values. Nonexhaustive sampling facilitates the use of quality metrics that take unique values at noninteger disparities. Depth estimates are iteratively refined with a stochastic cooperative search by perturbing the estimates, sampling match quality, and reweighting and aggregating the perturbations. The approach gains significant efficiencies when applied to video, where initial estimates are seeded using information from the previous pair in a novel application of the Z-buffering algorithm. This significantly reduces the number of search iterations required. We present a quantitative accuracy evaluation wherein the proposed method outperforms a microcanonical annealing approach by Barnard [2] and a cooperative approach by Zitnick and Kanade [27], while using fewer match quality evaluations than either. The approach is shown to have more attractive memory usage and scaling than alternatives based on exhaustive sampling.