CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild

Published in CVPR, 2022

Yang You, Ruoxi Shi, Weiming Wang, Cewu Lu

arXiv / PDF / code / project page / BibTeX

Abstract

This paper addresses category-level 9D pose estimation in the wild using a single RGB-D frame. Inspired by traditional point pair features (PPFs), we introduce a novel Category-level PPF (CPPF) voting method for accurate, robust, and generalizable 9D pose estimation. Our approach samples numerous point pairs on an object, predicting SE(3)-invariant voting statistics for object centers, orientations, and scales. We propose a coarse-to-fine voting algorithm to filter out noisy samples and refine predictions. An auxiliary binary classification task helps eliminate false positives in orientation voting. To ensure robustness, our sim-to-real pipeline trains on synthetic point clouds, except for geometrically ambiguous objects.

BibTeX

@inproceedings{you2022cppf,
  title     = {CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wild},
  author    = {Yang You and Ruoxi Shi and Weiming Wang and Cewu Lu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2022},
  eprint    = {2203.03089},
  archivePrefix = {arXiv}
}

Recommended citation: