Revisiting the PnP Problem with a GPS
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
1-point RANSAC for EKF-based structure from motion
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Simultaneous in-plane motion estimation and point matching using geometric cues only
WMVC'09 Proceedings of the 2009 international conference on Motion and video computing
Combining geometric and appearance priors for robust homography estimation
ECCV'10 Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III
Simultaneous Camera Pose and Correspondence Estimation with Motion Coherence
International Journal of Computer Vision
Random model variation for universal feature tracking
Proceedings of the 18th ACM symposium on Virtual reality software and technology
Hi-index | 0.00 |
Estimating a camera pose given a set of 3D-object and 2D-image feature points is a well understood problem when correspondences are given. However, when such correspondences cannot be established a priori, one must simultaneously compute them along with the pose. Most current approaches to solving this problem are too computationally intensive to be practical. An interesting exception is the SoftPosit algorithm, that looks for the solution as the minimum of a suitable objective function. It is arguably one of the best algorithms but its iterative nature means it can fail in the presence of clutter, occlusions, or repetitive patterns. In this paper, we propose an approach that overcomes this limitation by taking advantage of the fact that, in practice, some prior on the camera pose is often available. We model it as a Gaussian Mixture Model that we progressively refine by hypothesizing new correspondences. This rapidly reduces the number of potential matches for each 3D point and lets us explore the pose space more thoroughly than SoftPosit at a similar computational cost. We will demonstrate the superior performance of our approach on both synthetic and real data.