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

Di Y, Manhardt F, Wang G, Ji X, Navab N, Tombari F (2021)

Publication Type: Conference contribution

Publication year: 2021

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 12376-12385

Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision

Event location: Virtual, Online, CAN

ISBN: 9781665428125

DOI: 10.1109/ICCV48922.2021.01217

Abstract

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (i.e. 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 PnP/RANSACbased 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.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Google Inc. US United States (USA) (US) Tsinghua University CN China (CN)

How to cite

APA:

Di, Y., Manhardt, F., Wang, G., Ji, X., Navab, N., & Tombari, F. (2021). SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation. In Proceedings of the IEEE International Conference on Computer Vision (pp. 12376-12385). Virtual, Online, CAN: Institute of Electrical and Electronics Engineers Inc..

MLA:

Di, Yan, et al. "SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation." Proceedings of the 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, Virtual, Online, CAN Institute of Electrical and Electronics Engineers Inc., 2021. 12376-12385.

BibTeX: Download