Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud
Matching
- URL: http://arxiv.org/abs/2402.17372v1
- Date: Tue, 27 Feb 2024 10:10:12 GMT
- Title: Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud
Matching
- Authors: Matteo Bastico, Etienne Decenci\`ere, Laurent Cort\'e, Yannick
Tillier, David Ryckelynck
- Abstract summary: Point cloud matching is a crucial technique in computer vision, medical and robotics fields.
We propose a new technique, based on graph Laplacian eigenmaps, to match point clouds by taking into account fine local structures.
We show that the similarity between those aligned high-dimensional spaces provides a locally meaningful score to match shapes.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point cloud matching, a crucial technique in computer vision, medical and
robotics fields, is primarily concerned with finding correspondences between
pairs of point clouds or voxels. In some practical scenarios, emphasizing local
differences is crucial for accurately identifying a correct match, thereby
enhancing the overall robustness and reliability of the matching process.
Commonly used shape descriptors have several limitations and often fail to
provide meaningful local insights on the paired geometries. In this work, we
propose a new technique, based on graph Laplacian eigenmaps, to match point
clouds by taking into account fine local structures. To deal with the order and
sign ambiguity of Laplacian eigenmaps, we introduce a new operator, called
Coupled Laplacian, that allows to easily generate aligned eigenspaces for
multiple rigidly-registered geometries. We show that the similarity between
those aligned high-dimensional spaces provides a locally meaningful score to
match shapes. We initially evaluate the performance of the proposed technique
in a point-wise manner, specifically focusing on the task of object anomaly
localization using the MVTec 3D-AD dataset. Additionally, we define a new
medical task, called automatic Bone Side Estimation (BSE), which we address
through a global similarity score derived from coupled eigenspaces. In order to
test it, we propose a benchmark collecting bone surface structures from various
public datasets. Our matching technique, based on Coupled Laplacian,
outperforms other methods by reaching an impressive accuracy on both tasks. The
code to reproduce our experiments is publicly available at
https://github.com/matteo-bastico/CoupledLaplacian and in the Supplementary
Code.
Related papers
- Decoupled Local Aggregation for Point Cloud Learning [12.810517967372043]
We propose to decouple the explicit modelling of spatial relations from local aggregation.
We present DeLA, a lightweight point network, where in each learning stage relative spatial encodings are first formed.
DeLA achieves over 90% overall accuracy on ScanObjectNN and 74% mIoU on S3DIS Area 5.
arXiv Detail & Related papers (2023-08-31T08:21:29Z) - Adaptive Spot-Guided Transformer for Consistent Local Feature Matching [64.30749838423922]
We propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching.
ASTR models the local consistency and scale variations in a unified coarse-to-fine architecture.
arXiv Detail & Related papers (2023-03-29T12:28:01Z) - Learning Implicit Feature Alignment Function for Semantic Segmentation [51.36809814890326]
Implicit Feature Alignment function (IFA) is inspired by the rapidly expanding topic of implicit neural representations.
We show that IFA implicitly aligns the feature maps at different levels and is capable of producing segmentation maps in arbitrary resolutions.
Our method can be combined with improvement on various architectures, and it achieves state-of-the-art accuracy trade-off on common benchmarks.
arXiv Detail & Related papers (2022-06-17T09:40:14Z) - SE(3)-Equivariant Attention Networks for Shape Reconstruction in
Function Space [50.14426188851305]
We propose the first SE(3)-equivariant coordinate-based network for learning occupancy fields from point clouds.
In contrast to previous shape reconstruction methods that align the input to a regular grid, we operate directly on the irregular, unoriented point cloud.
We show that our method outperforms previous SO(3)-equivariant methods, as well as non-equivariant methods trained on SO(3)-augmented datasets.
arXiv Detail & Related papers (2022-04-05T17:59:15Z) - Seeking Similarities over Differences: Similarity-based Domain Alignment
for Adaptive Object Detection [86.98573522894961]
We propose a framework that generalizes the components commonly used by Unsupervised Domain Adaptation (UDA) algorithms for detection.
Specifically, we propose a novel UDA algorithm, ViSGA, that leverages the best design choices and introduces a simple but effective method to aggregate features at instance-level.
We show that both similarity-based grouping and adversarial training allows our model to focus on coarsely aligning feature groups, without being forced to match all instances across loosely aligned domains.
arXiv Detail & Related papers (2021-10-04T13:09:56Z) - Index $t$-SNE: Tracking Dynamics of High-Dimensional Datasets with
Coherent Embeddings [1.7188280334580195]
This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved.
The proposed algorithm has the same complexity as the original $t$-SNE to embed new items, and a lower one when considering the embedding of a dataset sliced into sub-pieces.
arXiv Detail & Related papers (2021-09-22T06:45:37Z) - PointFlow: Flowing Semantics Through Points for Aerial Image
Segmentation [96.76882806139251]
We propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow.
Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features.
Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods.
arXiv Detail & Related papers (2021-03-11T09:42:32Z) - Robust Kernel-based Feature Representation for 3D Point Cloud Analysis
via Circular Graph Convolutional Network [2.42919716430661]
We present a new local feature description method that is robust to rotation, density, and scale variations.
To improve representations of the local descriptors, we propose a global aggregation method.
Our method shows superior performances when compared to the state-of-the-art methods.
arXiv Detail & Related papers (2020-12-22T18:02:57Z) - Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences.
We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline.
Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z)
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.