Semi-Dense Visual Odometry for RGB-D Cameras Using Approximate Nearest Neighbour Fields

TL;DR

This paper introduces a robust semi-dense visual odometry method for RGB-D cameras that uses a 2D-3D ICP pipeline with approximate nearest neighbor fields, improving speed and accuracy over existing methods.

Contribution

The paper proposes a novel 2D-3D ICP-based visual odometry approach utilizing approximate nearest neighbor fields and robust optimization, enhancing robustness and efficiency.

Findings

Outperforms state-of-the-art methods on RGB-D datasets

Efficient registration using approximate nearest neighbor fields

Robust outlier handling with maximum a posteriori formulation

Abstract

This paper presents a robust and efficient semi-dense visual odometry solution for RGB-D cameras. The core of our method is a 2D-3D ICP pipeline which estimates the pose of the sensor by registering the projection of a 3D semi-dense map of the reference frame with the 2D semi-dense region extracted in the current frame. The processing is speeded up by efficiently implemented approximate nearest neighbour fields under the Euclidean distance criterion, which permits the use of compact Gauss-Newton updates in the optimization. The registration is formulated as a maximum a posterior problem to deal with outliers and sensor noises, and consequently the equivalent weighted least squares problem is solved by iteratively reweighted least squares method. A variety of robust weight functions are tested and the optimum is determined based on the characteristics of the sensor model. Extensive evaluation on publicly available RGB-D datasets shows that the proposed method predominantly outperforms existing state-of-the-art methods.