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

by   Yang You, et al.

In this paper, we tackle the problem of category-level 9D pose estimation in the wild, given a single RGB-D frame. Using supervised data of real-world 9D poses is tedious and erroneous, and also fails to generalize to unseen scenarios. Besides, category-level pose estimation requires a method to be able to generalize to unseen objects at test time, which is also challenging. Drawing inspirations from traditional point pair features (PPFs), in this paper, we design a novel Category-level PPF (CPPF) voting method to achieve accurate, robust and generalizable 9D pose estimation in the wild. To obtain robust pose estimation, we sample numerous point pairs on an object, and for each pair our model predicts necessary SE(3)-invariant voting statistics on object centers, orientations and scales. A novel coarse-to-fine voting algorithm is proposed to eliminate noisy point pair samples and generate final predictions from the population. To get rid of false positives in the orientation voting process, an auxiliary binary disambiguating classification task is introduced for each sampled point pair. In order to detect objects in the wild, we carefully design our sim-to-real pipeline by training on synthetic point clouds only, unless objects have ambiguous poses in geometry. Under this circumstance, color information is leveraged to disambiguate these poses. Results on standard benchmarks show that our method is on par with current state of the arts with real-world training data. Extensive experiments further show that our method is robust to noise and gives promising results under extremely challenging scenarios. Our code is available on https://github.com/qq456cvb/CPPF.


page 8

page 11


Go Beyond Point Pairs: A General and Accurate Sim2Real Object Pose Voting Method with Efficient Online Synthetic Training

Object pose estimation is an important topic in 3D vision. Though most c...

Generative Category-Level Shape and Pose Estimation with Semantic Primitives

Empowering autonomous agents with 3D understanding for daily objects is ...

3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation

In this paper, we focus on estimating the 6D pose of objects in point cl...

Zero-Shot Category-Level Object Pose Estimation

Object pose estimation is an important component of most vision pipeline...

Going Further with Point Pair Features

Point Pair Features is a widely used method to detect 3D objects in poin...

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

As a basic component of SE(3)-equivariant deep feature learning, steerab...

Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition

It is possible to associate a highly constrained subset of relative 6 Do...

Please sign up or login with your details

Forgot password? Click here to reset