A tutorial on $\mathbf{SE}(3)$ transformation parameterizations and
on-manifold optimization
- URL: http://arxiv.org/abs/2103.15980v1
- Date: Mon, 29 Mar 2021 22:43:49 GMT
- Title: A tutorial on $\mathbf{SE}(3)$ transformation parameterizations and
on-manifold optimization
- Authors: Jos\'e Luis Blanco-Claraco
- Abstract summary: An arbitrary rigid transformation in $mathbfSE(3)$ can be separated into two parts, namely, a translation and a rigid rotation.
This report reviews, under a unifying viewpoint, three common alternatives to representing the rotation part.
It will be described: (i) the equivalence between these representations and the formulas for transforming one to each other.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: An arbitrary rigid transformation in $\mathbf{SE}(3)$ can be separated into
two parts, namely, a translation and a rigid rotation. This technical report
reviews, under a unifying viewpoint, three common alternatives to representing
the rotation part: sets of three (yaw-pitch-roll) Euler angles, orthogonal
rotation matrices from $\mathbf{SO}(3)$ and quaternions. It will be described:
(i) the equivalence between these representations and the formulas for
transforming one to each other (in all cases considering the translational and
rotational parts as a whole), (ii) how to compose poses with poses and poses
with points in each representation and (iii) how the uncertainty of the poses
(when modeled as Gaussian distributions) is affected by these transformations
and compositions. Some brief notes are also given about the Jacobians required
to implement least-squares optimization on manifolds, an very promising
approach in recent engineering literature. The text reflects which MRPT C++
library functions implement each of the described algorithms. All formulas and
their implementation have been thoroughly validated by means of unit testing
and numerical estimation of the Jacobians
Related papers
- Learning Unorthogonalized Matrices for Rotation Estimation [83.94986875750455]
Estimating 3D rotations is a common procedure for 3D computer vision.
One form of representation -- rotation matrices -- is popular due to its continuity.
We propose unorthogonalized Pseudo' Rotation Matrices (PRoM)
arXiv Detail & Related papers (2023-12-01T09:56:29Z) - Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space [15.495593104596399]
We formalize the notion of weight sharing in convolutional networks as the sharing of message functions over point-pairs.
We develop an efficient equivariant group convolutional network for processing 3D point clouds.
arXiv Detail & Related papers (2023-10-04T17:06:32Z) - Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras
from First Principles [55.41644538483948]
We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset.
We use fully connected neural networks to model the transformations symmetry and the corresponding generators.
Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.
arXiv Detail & Related papers (2023-01-13T16:25:25Z) - Equivalence Between SE(3) Equivariant Networks via Steerable Kernels and
Group Convolution [90.67482899242093]
A wide range of techniques have been proposed in recent years for designing neural networks for 3D data that are equivariant under rotation and translation of the input.
We provide an in-depth analysis of both methods and their equivalence and relate the two constructions to multiview convolutional networks.
We also derive new TFN non-linearities from our equivalence principle and test them on practical benchmark datasets.
arXiv Detail & Related papers (2022-11-29T03:42:11Z) - 3D Equivariant Graph Implicit Functions [51.5559264447605]
We introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details.
Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 on the ShapeNet reconstruction task.
arXiv Detail & Related papers (2022-03-31T16:51:25Z) - Gaussian-Hermite Moment Invariants of General Vector Functions to
Rotation-Affine Transform [39.58178582162608]
In this paper, we focus on constructing moment invariants of general vector functions.
This is the first time that a uniform frame has been proposed in the literature to construct moment invariants.
Based on synthetic and popular datasets of vector-valued data, the experiments are carried out to evaluate the stability and discriminability of these invariants.
arXiv Detail & Related papers (2022-01-03T20:56:15Z) - Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image [1.8692254863855962]
We develop a rotation equivariant model for generating 3D hand meshes from 2D RGB images.
This guarantees that as the input image of a hand is rotated the generated mesh undergoes a corresponding rotation.
arXiv Detail & Related papers (2021-11-25T11:07:27Z) - A Practical Method for Constructing Equivariant Multilayer Perceptrons
for Arbitrary Matrix Groups [115.58550697886987]
We provide a completely general algorithm for solving for the equivariant layers of matrix groups.
In addition to recovering solutions from other works as special cases, we construct multilayer perceptrons equivariant to multiple groups that have never been tackled before.
Our approach outperforms non-equivariant baselines, with applications to particle physics and dynamical systems.
arXiv Detail & Related papers (2021-04-19T17:21:54Z) - Rotation-Invariant Point Convolution With Multiple Equivariant
Alignments [1.0152838128195467]
We show that using rotation-equivariant alignments, it is possible to make any convolutional layer rotation-invariant.
With this core layer, we design rotation-invariant architectures which improve state-of-the-art results in both object classification and semantic segmentation.
arXiv Detail & Related papers (2020-12-07T20:47:46Z) - Relative Pose Estimation of Calibrated Cameras with Known
$\mathrm{SE}(3)$ Invariants [65.2314683780204]
We present a complete study of the relative pose estimation problem for a camera constrained by known $mathrmSE(3)$ invariants.
These problems reduces the minimal number of point pairs for relative pose estimation.
Experiments on synthetic and real data shows performance improvement compared to conventional relative pose estimation methods.
arXiv Detail & Related papers (2020-07-15T13:55:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.