Related papers: Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation

Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation

URL: http://arxiv.org/abs/2309.09934v1
Date: Mon, 18 Sep 2023 16:51:56 GMT
Title: Hierarchical Attention and Graph Neural Networks: Toward Drift-Free Pose Estimation
Authors: Kathia Melbouci, Fawzi Nashashibi
Abstract summary: The most commonly used method for addressing 3D geometric registration is the iterative closet-point algorithm. We propose a framework that replaces traditional geometric registration and pose graph optimization with a learned model utilizing hierarchical attention mechanisms and graph neural networks.
Score: 1.745925556687899
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: The most commonly used method for addressing 3D geometric registration is the iterative closet-point algorithm, this approach is incremental and prone to drift over multiple consecutive frames. The Common strategy to address the drift is the pose graph optimization subsequent to frame-to-frame registration, incorporating a loop closure process that identifies previously visited places. In this paper, we explore a framework that replaces traditional geometric registration and pose graph optimization with a learned model utilizing hierarchical attention mechanisms and graph neural networks. We propose a strategy to condense the data flow, preserving essential information required for the precise estimation of rigid poses. Our results, derived from tests on the KITTI Odometry dataset, demonstrate a significant improvement in pose estimation accuracy. This improvement is especially notable in determining rotational components when compared with results obtained through conventional multi-way registration via pose graph optimization. The code will be made available upon completion of the review process.

Related papers

EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction [0.0]
We consider a one-shot OC approach that reconstructs particle tracks directly from a set of hits. This approach iteratively updates the graphs and can better facilitate the message passing across each graph. Preliminary studies on the TrackML dataset show better track performance compared to the methods that require a fixed input graph.
arXiv Detail & Related papers (2024-07-18T22:29:24Z)
Ensemble Quadratic Assignment Network for Graph Matching [52.20001802006391]
Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably. We propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
arXiv Detail & Related papers (2024-03-11T06:34:05Z)
Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding [51.75091298017941]
This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) for attributed graph data. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets.
arXiv Detail & Related papers (2024-01-12T17:57:07Z)
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting [63.95845583460312]
We present a new method for the multiview registration of point cloud. Our method achieves 11% higher registration recall on the 3DMatch dataset and 13% lower registration errors on the ScanNet dataset.
arXiv Detail & Related papers (2023-04-02T06:43:40Z)
Large-scale Point Cloud Registration Based on Graph Matching Optimization [30.92028761652611]
We propose a underlineGraph underlineMatching underlineOptimization based underlineNetwork. The proposed method has been evaluated on the 3DMatch/3DLoMatch benchmarks and the KITTI benchmark.
arXiv Detail & Related papers (2023-02-12T03:29:35Z)
A Complex Network based Graph Embedding Method for Link Prediction [0.0]
We present a novel graph embedding approach based on the popularity-similarity and local attraction paradigms. We show, using extensive experimental analysis, that the proposed method outperforms state-of-the-art graph embedding algorithms.
arXiv Detail & Related papers (2022-09-11T14:46:38Z)
Optimal Propagation for Graph Neural Networks [51.08426265813481]
We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
arXiv Detail & Related papers (2022-05-06T03:37:00Z)
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)
Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector [15.900382629390297]
We propose to develop a novel model that integrates the optimization to learning, aiming to address the technical challenges in 3D registration. In addition to the deep transformation decoding network, our framework introduce an optimizable deep underlineSpatial underlineCorrelation underlineRepresentation.
arXiv Detail & Related papers (2020-09-29T22:44:38Z)
Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College [80.67842220664231]
We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
arXiv Detail & Related papers (2020-06-10T14:48:48Z)

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