Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects

TL;DR

This paper introduces ICG, a fast and robust 3D object tracker that fuses region and depth data, effective even for textureless objects, outperforming current methods in accuracy and efficiency.

Contribution

The paper presents a novel probabilistic 3D tracking method that relies solely on object geometry, combining region and depth information with iterative refinement and occlusion handling.

Findings

Outperforms state-of-the-art methods in accuracy and robustness.

Requires only 1.3 ms per frame on a CPU, demonstrating high efficiency.

Effective for both textured and textureless objects across multiple datasets.

Abstract

Tracking objects in 3D space and predicting their 6DoF pose is an essential task in computer vision. State-of-the-art approaches often rely on object texture to tackle this problem. However, while they achieve impressive results, many objects do not contain sufficient texture, violating the main underlying assumption. In the following, we thus propose ICG, a novel probabilistic tracker that fuses region and depth information and only requires the object geometry. Our method deploys correspondence lines and points to iteratively refine the pose. We also implement robust occlusion handling to improve performance in real-world settings. Experiments on the YCB-Video, OPT, and Choi datasets demonstrate that, even for textured objects, our approach outperforms the current state of the art with respect to accuracy and robustness. At the same time, ICG shows fast convergence and outstanding efficiency, requiring only 1.3 ms per frame on a single CPU core. Finally, we analyze the influence of individual components and discuss our performance compared to deep learning-based methods. The source code of our tracker is publicly available.