In Search of Inliers: 3D Correspondence by Local and Global Voting

Abstract

We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a combination of local and global constraints to determine if a vote should be cast. On a local scale, we use simple, low-level geometric invariants. On a global scale, we apply covariant constraints for finding compatible correspondences. We guide the sampling for collecting voters by downward dependencies on previous voting stages. All of this together results in an accurate matching procedure. We evaluate our algorithm by controlled and comparative testing on different datasets, giving superior performance compared to state of the art methods. In a final experiment, we apply our method for 3D object detection, showing potential use of our method within higher-level vision.

Spatially Stratified Correspondence Sampling for Real-Time Point Cloud Tracking

“…In both synthetic and real cases, input consists of RGB-D sequences. Trackers were initialized using an external pose -in the synthetic case, from ground truth, and in the real case, using a pose estimation algorithm [2]. Object models were generated by registering multiple views of the objects using the same RGB-D sensor employed for tracking.…”

“…This set consists of eight pieces which can be assembled in a number of different orders. In our experiments, models consist of voxelized point clouds derived from high-resolution models of the pieces, and initial poses for tracking are found using a combined object recognition and pose estimation algorithm [2]. Each object is tracked using an independent particle filter, with N samples set to 50, and N particles set to 1000.…”

Urban 3D segmentation and modelling from street view images and LiDAR point clouds

“…These methods and also many direct point cloud-based methods, e.g. [4,15,28], are designed to recognize a specific object stored as a point cloud model, and therefore practical use of these methods for urban 3D often requires various geometric features to robustify matching [38]. Urban 3D segmentation Most of the existing city modelling approaches directly or indirectly tackle the problem through 3D point cloud analysis.…”

Multi-attribute statistics histograms for accurate and robust pairwise registration of range images

“…In terms of transformation estimation, the random sample consensus (RANSAC) [32] is a commonly-used method in both 2D and 3D registration cases, and shows some specific advantages, e.g., low implementation complexity and very few tunable parameters, against other approaches such as 3D Hough transform [33] , the rigidity constrain framework [34] and voting-based approach [35] . In 3D registration case, owing to that additional geometry information and/or constrains can be explored, many variants of RANSAC are thereupon proposed to either improve its time efficiency and/or robustness.…”