Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

Lahav Lipson, Zachary Teed, Ankit Goyal, Jia Deng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6728-6737

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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lipson_2022_CVPR, author = {Lipson, Lahav and Teed, Zachary and Goyal, Ankit and Deng, Jia}, title = {Coupled Iterative Refinement for 6D Multi-Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {6728-6737} }