Category-Level Articulated Object Pose Estimation
Xiaolong Li,He Wang,Li Yi,Leonidas J. Guibas,A. Lynn Abbott,Shuran Song +5 more
- pp 3706-3715
Reads0
Chats0
TLDR
A deep network based on PointNet++ is developed that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space, and leveraging the canonicalized joints are demonstrated.Abstract:
This paper addresses the task of category-level pose estimation for articulated objects from a single depth image. We present a novel category-level approach that correctly accommodates object instances previously unseen during training. We introduce Articulation-aware Normalized Coordinate Space Hierarchy (ANCSH) – a canonical representation for different articulated objects in a given category. As the key to achieve intra-category generalization, the representation constructs a canonical object space as well as a set of canonical part spaces. The canonical object space normalizes the object orientation, scales and articulations (e.g. joint parameters and states) while each canonical part space further normalizes its part pose and scale. We develop a deep network based on PointNet++ that predicts ANCSH from a single depth point cloud, including part segmentation, normalized coordinates, and joint parameters in the canonical object space. By leveraging the canonicalized joints, we demonstrate: 1) improved performance in part pose and scale estimations using the induced kinematic constraints from joints; 2) high accuracy for joint parameter estimation in camera space.read more
Citations
More filters
Proceedings ArticleDOI
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
TL;DR: In this article, a joint learning framework for estimating 3D hand and object pose from a single image is proposed, where the spatial-temporal consistency in large-scale hand-object videos is used as a constraint for generating pseudo labels in semi-supervised learning.
Posted Content
CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
TL;DR: In this paper, the authors propose a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations (CaSPR) to enable information aggregation over time and the interrogation of object state at any spatio-temporal neighborhood.
Posted Content
ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory
TL;DR: Results demonstrate that ScrewNet can successfully estimate the articulation models and their parameters for novel objects across articulation model categories with better on average accuracy than the prior state-of-the-art method.
Proceedings ArticleDOI
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
Jiahui Huang,He Wang,Tolga Birdal,Minhyuk Sung,Federica Arrigoni,Shi-Min Hu,Leonidas J. Guibas +6 more
TL;DR: MultiBodySync as discussed by the authors proposes an end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds, which incorporates spectral synchronization into an iterative deep declarative network.
Posted Content
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
TL;DR: In this paper, the authors propose a vector neuron representation for the SO(3)-equivariance to the rotation group of pointclouds, which can be extended from 1D scalars to 3D vectors.
References
More filters
Journal ArticleDOI
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Journal ArticleDOI
A method for registration of 3-D shapes
Paul J. Besl,H.D. McKay +1 more
TL;DR: In this paper, the authors describe a general-purpose representation-independent method for the accurate and computationally efficient registration of 3D shapes including free-form curves and surfaces, based on the iterative closest point (ICP) algorithm, which requires only a procedure to find the closest point on a geometric entity to a given point.
Posted Content
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TL;DR: A hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set and proposes novel set learning layers to adaptively combine features from multiple scales to learn deep point set features efficiently and robustly.
Proceedings Article
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
TL;DR: PointNet++ as discussed by the authors applies PointNet recursively on a nested partitioning of the input point set to learn local features with increasing contextual scales, and proposes novel set learning layers to adaptively combine features from multiple scales.
Journal ArticleDOI
Least-squares estimation of transformation parameters between two point patterns
TL;DR: The proposed theorem is a strict solution of the problem, and it always gives the correct transformation parameters even when the data is corrupted.