Related papers: Geodesic squared exponential kernel for non-rigid shape registration

Geodesic squared exponential kernel for non-rigid shape registration

URL: http://arxiv.org/abs/2112.11853v1
Date: Wed, 22 Dec 2021 13:01:00 GMT
Title: Geodesic squared exponential kernel for non-rigid shape registration
Authors: Florent Jousse (UCA, Qc, EPIONE), Xavier Pennec (UCA, EPIONE), Herv\'e Delingette (UCA, EPIONE), Matilde Gonzalez (Qc)
Abstract summary: This work addresses the problem of non-rigid registration of 3D scans. We propose a new kernel based on geodesic for the Gaussian Process Morphable Models framework. We show that the Geodesic squared exponential kernel performs significantly better than state of the art kernels for the task of face registration.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: This work addresses the problem of non-rigid registration of 3D scans, which is at the core of shape modeling techniques. Firstly, we propose a new kernel based on geodesic distances for the Gaussian Process Morphable Models (GPMMs) framework. The use of geodesic distances into the kernel makes it more adapted to the topological and geometric characteristics of the surface and leads to more realistic deformations around holes and curved areas. Since the kernel possesses hyperparameters we have optimized them for the task of face registration on the FaceWarehouse dataset. We show that the Geodesic squared exponential kernel performs significantly better than state of the art kernels for the task of face registration on all the 20 expressions of the FaceWarehouse dataset. Secondly, we propose a modification of the loss function used in the non-rigid ICP registration algorithm, that allows to weight the correspondences according to the confidence given to them. As a use case, we show that we can make the registration more robust to outliers in the 3D scans, such as non-skin parts.

Related papers

3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
arXiv Detail & Related papers (2024-11-01T12:50:38Z)
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions [93.02515761070201]
We present a novel type of neural fields that uses general radial bases for signal representation. Our method builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed.
arXiv Detail & Related papers (2023-09-27T06:32:05Z)
NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries [77.04220651098723]
This paper presents the first attempt to represent geodesics on 3D mesh models using neural implicit functions. Specifically, we introduce neural geodesic fields (NeuroGFs), which are learned to represent the all-pairs geodesics of a given mesh. NeuroGFs exhibit exceptional performance in solving the single-source all-destination (SSAD) and point-to-point geodesics.
arXiv Detail & Related papers (2023-06-01T13:32:21Z)
Probabilistic Registration for Gaussian Process 3D shape modelling in the presence of extensive missing data [63.8376359764052]
We propose a shape fitting/registration method based on a Gaussian Processes formulation, suitable for shapes with extensive regions of missing data. Experiments are conducted both for a 2D small dataset with diverse transformations and a 3D dataset of ears.
arXiv Detail & Related papers (2022-03-26T16:48:27Z)
Towards Fine-grained 3D Face Dense Registration: An Optimal Dividing and Diffusing Method [17.38748022631488]
Dense-to-vertex correspondence between 3D faces is a fundamental and challenging issue for 3D&2D face analysis. In this paper, we revisit dense registration by a dimension-degraded problem, i.e. proportional segmentation of a line. We employ an iterative dividing and diffusing method to reach the final solution uniquely.
arXiv Detail & Related papers (2021-09-23T08:31:35Z)
Self-supervised Geometric Perception [96.89966337518854]
Self-supervised geometric perception is a framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels. We show that SGP achieves state-of-the-art performance that is on-par or superior to the supervised oracles trained using ground-truth labels.
arXiv Detail & Related papers (2021-03-04T15:34:43Z)
Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment [85.32080531133799]
This paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy.
arXiv Detail & Related papers (2020-12-15T11:42:17Z)
Cortical surface registration using unsupervised learning [8.57142014602892]
Non-rigid cortical registration is an important and challenging task due to the geometric complexity of the human cortex. Recent learning-based methods to surfaces yields poor results due to distortions introduced by projecting a sphere to a 2D plane. We present SphereMorph, a diffeomorphic registration framework for cortical surfaces using deep networks that addresses these issues.
arXiv Detail & Related papers (2020-04-09T15:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.