DeepAI AI Chat
Log In Sign Up

Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences

by   Jun-Jee Chao, et al.
University of Minnesota

Correspondence search is an essential step in rigid point cloud registration algorithms. Most methods maintain a single correspondence at each step and gradually remove wrong correspondances. However, building one-to-one correspondence with hard assignments is extremely difficult, especially when matching two point clouds with many locally similar features. This paper proposes an optimization method that retains all possible correspondences for each keypoint when matching a partial point cloud to a complete point cloud. These uncertain correspondences are then gradually updated with the estimated rigid transformation by considering the matching cost. Moreover, we propose a new point feature descriptor that measures the similarity between local point cloud regions. Extensive experiments show that our method outperforms the state-of-the-art (SoTA) methods even when matching different objects within the same category. Notably, our method outperforms the SoTA methods when registering real-world noisy depth images to a template shape by up to 20 performance.


A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration

3D point cloud registration in remote sensing field has been greatly adv...

Multi-Features Guidance Network for partial-to-partial point cloud registration

To eliminate the problems of large dimensional differences, big semantic...

Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds

This paper presents a novel unsupervised approach to reconstruct human s...

Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes

We propose an unsupervised learning framework with the pretext task of f...

Deep Hough Voting for Robust Global Registration

Point cloud registration is the task of estimating the rigid transformat...

Searching Dense Point Correspondences via Permutation Matrix Learning

Although 3D point cloud data has received widespread attentions as a gen...

Dynamical Pose Estimation

We study the problem of aligning two sets of 3D geometric primitives giv...