Geo6D: Geometric Constraints Learning for 6D Pose Estimation

TL;DR

Geo6D introduces a geometric constraints learning approach for 6D pose estimation, enhancing the accuracy and robustness of direct regression methods by explicitly modeling pose transformations and reducing data requirements.

Contribution

The paper proposes Geo6D, a novel geometric constraints learning method that improves 6D pose estimation by incorporating explicit pose transformation formulas and relative offset representations.

Findings

Achieves state-of-the-art results on multiple datasets.

Effective even with only 10% of training data.

Significantly improves robustness of direct regression methods.

Abstract

Numerous 6D pose estimation methods have been proposed that employ end-to-end regression to directly estimate the target pose parameters. Since the visible features of objects are implicitly influenced by their poses, the network allows inferring the pose by analyzing the differences in features in the visible region. However, due to the unpredictable and unrestricted range of pose variations, the implicitly learned visible feature-pose constraints are insufficiently covered by the training samples, making the network vulnerable to unseen object poses. To tackle these challenges, we proposed a novel geometric constraints learning approach called Geo6D for direct regression 6D pose estimation methods. It introduces a pose transformation formula expressed in relative offset representation, which is leveraged as geometric constraints to reconstruct the input and output targets of the network. These reconstructed data enable the network to estimate the pose based on explicit geometric constraints and relative offset representation mitigates the issue of the pose distribution gap. Extensive experimental results show that when equipped with Geo6D, the direct 6D methods achieve state-of-the-art performance on multiple datasets and demonstrate significant effectiveness, even with only 10% amount of data.