Depth-map merging is one typical technique category for multi-view stereo (MVS) reconstruction. To guarantee accuracy, existing algorithms usually require either sub-pixel level stereo matching precision or continuous depth-map estimation. The merging of inaccurate depth-maps remains a challenging problem. This paper introduces a bundle optimization method for robust and accurate depth-map merging. In the method, depth-maps are generated using DAISY feature, followed by two stages of bundle optimization. The ﬁrst stage optimizes the track of connected stereo matches to generate initial 3D points. The second stage optimizes the position and normals of 3D points. High quality point cloud is then meshed as geometric models.
The proposed method can be easily parallelizable on multi-core processors. Middlebury evaluation shows that it is one of the most efﬁcient methods among non-GPU algorithms, yet still keeps very high accuracy. We also demonstrate the effectiveness of the proposed algorithm on various real-world, high-resolution, self-calibrated data sets including objects with complex details, objects with large area of highlight, and objects with non-Lambertian surface.Paper
[demo videos] (18.6MB)Datasets
All photos are by Canon IXUS 970 digital camera.
The created mesh results for all the 3 datasets [mesh-file](11MB)
The readme file describes the format for camera parameters.
We thank S. Seitz, B. Curless, J. Diebel, D. Scharstein, and R. Szeliski for the setup of the Middlebury evaluation, and D. Scharstein for the great help of the evaluation of our results.
Thanks also go to Intel colleagues Jim Hurley and Horst Haussecker for their supports to our project.
Note Yimin Zhang made no contribution to any of my projects/publications.