Abstract
Depth and surface normal estimation are crucial components in understanding 3D scene geometry from calibrated stereo images. In this paper, we propose visibility and disparity magnitude constraints for slanted patches in the scene. These constraints can be used to associate geometrically feasible planes with each point in the disparity space. The new constraints are validated in the PatchMatch Stereo framework. We use these new constraints not only for initialization, but also in the local plane refinement step of this iterative algorithm. The proposed constraints increase the probability of estimating correct plane parameters, and lead to an improved 3D reconstruction of the scene. Furthermore, the proposed constrained initialization reduces the number of iterations before convergence to the optimal plane parameters. In addition, as most stereo image pairs are not perfectly rectified, we modify the view propagation process by assigning the plane parameters to the neighbors of the candidate pixel. To update the plane parameters in the plane refinement step, we use a gradient free non-linear optimizer. The benefits of the new initialization, propagation, and refinement schemes are demonstrated.
Highlights
A CCURATE depth estimation from stereo images is important in many applications, such as augmented reality [1], terrain estimation [2], mapping [3], navigation [4], scene segmentation [5], object recognition [6] and 3D reconstruction [7]
We present a constrained initialization scheme that works with any algorithm that can be cast in the PatchMatch Stereo (PMS) framework
In our modified view propagation, we address this problem by assigning plane parameters to the immediate neighbors of the candidate pixels
Summary
A CCURATE depth estimation from stereo images is important in many applications, such as augmented reality [1], terrain estimation [2], mapping [3], navigation [4], scene segmentation [5], object recognition [6] and 3D reconstruction [7]. Algorithms [9]–[11] use the PMS framework to reconstruct the visible surfaces in the disparity space [12] defined by the pixel coordinates and the possible disparities. The reconstruction is based on associating a slanted plane with each candidate match, in contrast with methods that evaluate the complete disparity space image, either explicitly, or by searching over the range of disparities at each pixel.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
