Dynamical Pose Estimation
arXiv:2103.06182
Abstract
We study the problem of aligning two sets of 3D geometric primitives given known correspondences. Our first contribution is to show that this primitive alignment framework unifies five perception problems including point cloud registration, primitive (mesh) registration, category-level 3D registration, absolution pose estimation (APE), and category-level APE. Our second contribution is to propose DynAMical Pose estimation (DAMP), the first general and practical algorithm to solve primitive alignment problem by simulating rigid body dynamics arising from virtual springs and damping, where the springs span the shortest distances between corresponding primitives. We evaluate DAMP in simulated and real datasets across all five problems, and demonstrate (i) DAMP always converges to the globally optimal solution in the first three problems with 3D-3D correspondences; (ii) although DAMP sometimes converges to suboptimal solutions in the last two problems with 2D-3D correspondences, using a scheme for escaping local minima, DAMP always succeeds. Our third contribution is to demystify the surprising empirical performance of DAMP and formally prove a global convergence result in the case of point cloud registration by charactering local stability of the equilibrium points of the underlying dynamical system.
arXiv commentICCV 2021 camera ready. Code: https://github.com/hankyang94/DAMP. Video: https://youtu.be/CDYXR1h98Q4
References in corpus (7)
- A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
- Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection
- Supervised Fitting of Geometric Primitives to 3D Point Clouds
- Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
- Optimal Pose and Shape Estimation for Category-level 3D Object Perception
- Pose Estimation for Non-Cooperative Rendezvous Using Neural Networks
- Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations