BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation

TL;DR

BiCo-Net introduces a novel approach combining local point pair matching and global pose regression to improve 6D object pose estimation robustness under occlusion and noise, achieving state-of-the-art results.

Contribution

The paper presents BiCo-Net, a new network that integrates local point pair matching with global pose regression for more robust 6D pose estimation.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Robust against occlusion and noisy depth images.

Effective in challenging real-world scenarios.

Abstract

The challenges of learning a robust 6D pose function lie in 1) severe occlusion and 2) systematic noises in depth images. Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space. To this end, we propose a novel Bi-directional Correspondence Mapping Network (BiCo-Net) to first generate point clouds guided by a typical pose regression, which can thus incorporate pose-sensitive information to optimize generation of local coordinates and their normal vectors. As pose predictions via geometric computation only rely on one single pair of local oriented points, our BiCo-Net can achieve robustness against sparse and occluded point clouds. An ensemble of redundant pose predictions from locally matching and direct pose regression further refines final pose output against noisy observations. Experimental results on three popularly benchmarking datasets can verify that our method can achieve state-of-the-art performance, especially for the more challenging severe occluded scenes. Source codes are available at https://github.com/Gorilla-Lab-SCUT/BiCo-Net.