Joint-Loss Enhanced Self-Supervised Learning for Refinement-Coupled Object 6D Pose Estimation
Fengjun Mu, Shixiang Sun, Rui Huang, Chaobin Zou, Wenjiang Li, Huayi Zhan, Hong Cheng
Abstract
6D object pose estimation plays a crucial role in robot grasping and manipulation. However, the prevalent methods for 6D object pose estimation heavily rely on 6D annotated data to train deep neural networks, which poses challenges due to the difficulty in obtaining sufficient pose annotations. To address this limitation, this paper presents a self-supervised pose estimation method based on a novel pixelwise weighted dense fusion architecture. This method allows for direct learning from unannotated RGB-D data facilitated by an Iterative Annotation Resolver. Furthermore, a self-supervised pose refinement method based on joint loss is proposed to enhance the pose estimation accuracy. This refinement method employs a differentiable renderer to construct joint optimization constraints. The experimental results demonstrate that our approach achieves a level of pose estimation accuracy that closely rivals that of supervised methods.
BibTeX
@inproceedings{icra2024_jointlossenhance,
title = {Joint-Loss Enhanced Self-Supervised Learning for Refinement-Coupled Object 6D Pose Estimation},
author = {Fengjun Mu and Shixiang Sun and Rui Huang and Chaobin Zou and Wenjiang Li and Huayi Zhan and Hong Cheng},
booktitle = {ICRA 2024},
year = {2024}
}