SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

TL;DR

SO-Pose introduces a novel approach that leverages self-occlusion reasoning to improve the accuracy of direct 6D pose estimation from a single RGB image, outperforming existing methods.

Contribution

The paper proposes a two-layer object representation and a fusion framework that enhances end-to-end 6D pose estimation accuracy by incorporating self-occlusion information.

Findings

Outperforms state-of-the-art methods on challenging datasets.

Achieves higher accuracy in cluttered environments.

Demonstrates robustness through cross-layer consistency.

Abstract

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (e.g. the 3D rotation and translation) in a cluttered environment from a single RGB image is a challenging problem. While end-to-end methods have recently demonstrated promising results at high efficiency, they are still inferior when compared with elaborate P$n$P/RANSAC-based approaches in terms of pose accuracy. In this work, we address this shortcoming by means of a novel reasoning about self-occlusion, in order to establish a two-layer representation for 3D objects which considerably enhances the accuracy of end-to-end 6D pose estimation. Our framework, named SO-Pose, takes a single RGB image as input and respectively generates 2D-3D correspondences as well as self-occlusion information harnessing a shared encoder and two separate decoders. Both outputs are then fused to directly regress the 6DoF pose parameters. Incorporating cross-layer consistencies that align correspondences, self-occlusion and 6D pose, we can further improve accuracy and robustness, surpassing or rivaling all other state-of-the-art approaches on various challenging datasets.