Correspondence-Free Pose Estimation with Patterns: A Unified Approach for Multi-Dimensional Vision
This addresses pose estimation for robotics, offering a flexible alternative to correspondence-based methods, but appears incremental as it builds on existing correspondence-free approaches.
The paper tackles the problem of 6D pose estimation in robot vision by proposing a correspondence-free method that eliminates unknowns to separate pose from correspondence, applicable to various transformations like perspective projection. Experimental results on simulation and actual data demonstrate its effectiveness.
6D pose estimation is a central problem in robot vision. Compared with pose estimation based on point correspondences or its robust versions, correspondence-free methods are often more flexible. However, existing correspondence-free methods often rely on feature representation alignment or end-to-end regression. For such a purpose, a new correspondence-free pose estimation method and its practical algorithms are proposed, whose key idea is the elimination of unknowns by process of addition to separate the pose estimation from correspondence. By taking the considered point sets as patterns, feature functions used to describe these patterns are introduced to establish a sufficient number of equations for optimization. The proposed method is applicable to nonlinear transformations such as perspective projection and can cover various pose estimations from 3D-to-3D points, 3D-to-2D points, and 2D-to-2D points. Experimental results on both simulation and actual data are presented to demonstrate the effectiveness of the proposed method.