@inproceedings{4d35493e5b654db88c6e020526aaffb7,
title = "Coupled Iterative Refinement for 6D Multi-Object Pose Estimation",
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. Code is available at https://github.com/princeton-vl/Coupled-Iterative-Refinement.",
keywords = "Deep learning architectures and techniques, Pose estimation and tracking",
author = "Lahav Lipson and Zachary Teed and Ankit Goyal and Jia Deng",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 ; Conference date: 19-06-2022 Through 24-06-2022",
year = "2022",
doi = "10.1109/CVPR52688.2022.00661",
language = "English (US)",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "6718--6727",
booktitle = "Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022",
address = "United States",
}