Coupled Iterative Refinement for 6d Multi-Object Pose Estimation

Lahav Lipson, Zachary Teed, Ankit Goyal, Jia Deng

CVPR 2022 pp. 6728-6737

doi:10.1109/CVPR52688.2022.00661 /cvpr/2022/lipson2022cvpr-coupled/

Abstract

We address the task of 6D multi-object pose: given a set of known 3D objects and an RGB or RGB-D input image, we detect and estimate the 6D pose of each object. We propose a new approach to 6D object pose estimation which consists of an end-to-end differentiable architecture that makes use of geometric knowledge. Our approach iteratively refines both pose and correspondence in a tightly coupled manner, allowing us to dynamically remove outliers to improve accuracy. We use a novel differentiable layer to perform pose refinement by solving an optimization problem we refer to as Bidirectional Depth-Augmented Perspective-N-Point (BD-PnP). Our method achieves state-of-the-art accuracy on standard 6D Object Pose benchmarks.

PDF CVPR Semantic Scholar

Cite

Text

Lipson et al. "Coupled Iterative Refinement for 6d Multi-Object Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2022. doi:10.1109/CVPR52688.2022.00661

Markdown

[Lipson et al. "Coupled Iterative Refinement for 6d Multi-Object Pose Estimation." Conference on Computer Vision and Pattern Recognition, 2022.](https://mlanthology.org/cvpr/2022/lipson2022cvpr-coupled/) doi:10.1109/CVPR52688.2022.00661

BibTeX

@inproceedings{lipson2022cvpr-coupled,
  title     = {{Coupled Iterative Refinement for 6d Multi-Object Pose Estimation}},
  author    = {Lipson, Lahav and Teed, Zachary and Goyal, Ankit and Deng, Jia},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2022},
  pages     = {6728-6737},
  doi       = {10.1109/CVPR52688.2022.00661},
  url       = {https://mlanthology.org/cvpr/2022/lipson2022cvpr-coupled/}
}