Leveraging se (3) equivariance for learning 3d geometric shape assembly
Shape assembly aims to reassemble parts (or fragments) into a complete object, which is a
common task in our daily life. Different from the semantic part assembly (eg, assembling a …
common task in our daily life. Different from the semantic part assembly (eg, assembling a …
Efem: Equivariant neural field expectation maximization for 3d object segmentation without scene supervision
Abstract We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple,
effective, and robust geometric algorithm that can segment objects in 3D scenes without …
effective, and robust geometric algorithm that can segment objects in 3D scenes without …
Banana: Banach fixed-point network for pointcloud segmentation with inter-part equivariance
Equivariance has gained strong interest as a desirable network property that inherently
ensures robust generalization. However, when dealing with complex systems such as …
ensures robust generalization. However, when dealing with complex systems such as …
Neuse: Neural se (3)-equivariant embedding for consistent spatial understanding with objects
We present NeuSE, a novel Neural SE (3)-Equivariant Embedding for objects, and illustrate
how it supports object SLAM for consistent spatial understanding with long-term scene …
how it supports object SLAM for consistent spatial understanding with long-term scene …
Rotation invariance and equivariance in 3D deep learning: a survey
J Fei, Z Deng - Artificial Intelligence Review, 2024 - Springer
Deep neural networks (DNNs) in 3D scenes show a strong capability of extracting high-level
semantic features and significantly promote research in the 3D field. 3D shapes and scenes …
semantic features and significantly promote research in the 3D field. 3D shapes and scenes …
Deep learning-based low overlap point cloud registration for complex scenario: The review
Most studies on point cloud registration have established the problem in the case of ideal
point cloud data. Although the state-of-the-art approaches have achieved amazing results …
point cloud data. Although the state-of-the-art approaches have achieved amazing results …
Approximately Piecewise E (3) Equivariant Point Networks
Integrating a notion of symmetry into point cloud neural networks is a provably effective way
to improve their generalization capability. Of particular interest are $ E (3) $ equivariant point …
to improve their generalization capability. Of particular interest are $ E (3) $ equivariant point …
HEGN: Hierarchical Equivariant Graph Neural Network for 9DoF Point Cloud Registration
Given its wide application in robotics, point cloud registration is a widely researched topic.
Conventional methods aim to find a rotation and translation that align two point clouds in 6 …
Conventional methods aim to find a rotation and translation that align two point clouds in 6 …
BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding
Dynamic scene understanding remains a persistent challenge in robotic applications. Early
dynamic mapping methods focused on mitigating the negative influence of short-term …
dynamic mapping methods focused on mitigating the negative influence of short-term …
Point Data Registration with the Multi-Object, Cardinalized Optimal Linear Assignment Metric
P Barrios, V Guzmán, M Adams, CA Perez - IEEE Access, 2024 - ieeexplore.ieee.org
Point cloud registration is a critical component of many tasks including the estimation of
sensor motion and 3D reconstruction. The Iterative Closest Point (ICP) algorithm and its …
sensor motion and 3D reconstruction. The Iterative Closest Point (ICP) algorithm and its …