Efficient and Outlier-Robust Simultaneous Pose and Correspondence Determination by Branch-and-Bound and Transformation Decomposition

Chen Wang∗, Yinlong Liu∗, Yiru Wang, Xuechen Li and Manning Wang†

IEEE Transactions on Pattern Analysis and Machine Intelligence (2021, IF=16.389)

Abstract

Estimating the pose of a calibrated camera relative to a 3D point-set from one image is an important task in computer vision. Perspective-n-Point algorithms are often used if perfect 2D-3D correspondences are known. However, it is difficult to determine 2D-3D correspondences perfectly, and then the simultaneous pose and correspondence determination problem is needed to be solved. Early methods aimed to solve this problem by local optimization. Recently, several new methods are proposed to globally solve this problem by using branch-and-bound (BnB) method, but they tend to be slow because the time complexity of the BnB-based method is exponential to the dimensionality of the parameter space, and they directly search the 6D parameter space. In this paper, we propose to decompose the searching to two separate searching processes by introducing a rotation invariant feature (RIF). Specifically, we construct RIFs from the original 3D and 2D point-sets and search for the globally optimal translation to match these two RIFs first. Then, the original 3D point set is translated and matched with the 2D point-set to find a globally optimal rotation. Experiments on challenging data show that the proposed method outperforms state-of-the-art methods in terms of both speed and accuracy.

Paper Link: https://ieeexplore.ieee.org/document/9485090