StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks

• URL: http://arxiv.org/abs/2002.03983v3
• Date: Fri, 19 Feb 2021 09:18:05 GMT
• Title: StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks
• Authors: Kai Fischer, Martin Simon, Florian Oelsner, Stefan Milz, Horst-Michael Gross, Patrick Maeder
• Abstract summary: StickyPillars is a fast, accurate and extremely robust deep middle-end 3D feature matching method on point clouds. We present state-of-art art accuracy results on the registration problem demonstrated on the KITTI dataset. We integrate our matching system into a LiDAR odometry pipeline yielding most accurate results on the KITTI dataset.
• Score: 16.940377259203284
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust point cloud registration in real-time is an important prerequisite for many mapping and localization algorithms. Traditional methods like ICP tend to fail without good initialization, insufficient overlap or in the presence of dynamic objects. Modern deep learning based registration approaches present much better results, but suffer from a heavy run-time. We overcome these drawbacks by introducing StickyPillars, a fast, accurate and extremely robust deep middle-end 3D feature matching method on point clouds. It uses graph neural networks and performs context aggregation on sparse 3D key-points with the aid of transformer based multi-head self and cross-attention. The network output is used as the cost for an optimal transport problem whose solution yields the final matching probabilities. The system does not rely on hand crafted feature descriptors or heuristic matching strategies. We present state-of-art art accuracy results on the registration problem demonstrated on the KITTI dataset while being four times faster then leading deep methods. Furthermore, we integrate our matching system into a LiDAR odometry pipeline yielding most accurate results on the KITTI odometry dataset. Finally, we demonstrate robustness on KITTI odometry. Our method remains stable in accuracy where state-of-the-art procedures fail on frame drops and higher speeds.

Related papers

• Deep Loss Convexification for Learning Iterative Models [11.36644967267829]
  Iterative methods such as iterative closest point (ICP) for point cloud registration often suffer from bad local optimality. We propose learning to form a convex landscape around each ground truth.
  arXiv  Detail & Related papers  (2024-11-16T01:13:04Z)
• DIPR: Efficient Point Cloud Registration via Dynamic Iteration [4.491867613612359]
  We introduce a novel Efficient Point Cloud Registration via Dynamic It framework, DIPR, that makes the neural network interactively focus on overlapping points based on sparser input points. Our proposed approach achieves superior registration accuracy while significantly reducing computational time and GPU memory consumption compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-05T16:47:46Z)
• GAFAR: Graph-Attention Feature-Augmentation for Registration A Fast and Light-weight Point Set Registration Algorithm [12.592563880121816]
  rigid registration of point clouds is a fundamental problem in computer vision. Deep learning in computer vision has brought new drive to research on this topic. We present a novel fast and light-weight network architecture using the attention mechanism to augment point descriptors.
  arXiv  Detail & Related papers  (2023-07-05T14:50:36Z)
• TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels [141.29156234353133]
  State-of-the-art convex learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. We show this disparity can largely be attributed to challenges presented by non-NISTity. We propose a Train-Convexify neural network (TCT) procedure to sidestep this issue.
  arXiv  Detail & Related papers  (2022-07-13T16:58:22Z)
• Learning Dense Features for Point Cloud Registration Using Graph Attention Network [0.0]
  We introduce a framework that efficiently and economically extracts dense features using graph attention network for point cloud matching and registration. The detector of the DFGAT is responsible for finding highly reliable key points in large raw data sets. The graph attention network uses the attention mechanism that enriches the relationships between point clouds.
  arXiv  Detail & Related papers  (2022-06-14T10:28:57Z)
• IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment [58.8330387551499]
  We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) We propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-03-22T10:14:08Z)
• DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
  We present a novel learning-based alignment network for complex alignment scenes. We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-11-15T08:27:21Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Self-Supervised Multi-Frame Monocular Scene Flow [61.588808225321735]
  We introduce a multi-frame monocular scene flow network based on self-supervised learning. We observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.
  arXiv  Detail & Related papers  (2021-05-05T17:49:55Z)
• RPM-Net: Robust Point Matching using Learned Features [79.52112840465558]
  RPM-Net is a less sensitive and more robust deep learning-based approach for rigid point cloud registration. Unlike some existing methods, our RPM-Net handles missing correspondences and point clouds with partial visibility.
  arXiv  Detail & Related papers  (2020-03-30T13:45:27Z)
• 3DSSD: Point-based 3D Single Stage Object Detector [61.67928229961813]
  We present a point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well.
  arXiv  Detail & Related papers  (2020-02-24T12:01:58Z)

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.