StickyPillars: Robust feature matching on point clouds using Graph Neural Networks
Explore this paper's citation graph
Summary
StickyPillars introduces a sparse feature matching method on point clouds that outperforms state-of-the art matching algorithms, while providing real-time capability.
- Type
- article
- Published
- 2020-02-10
- Cited by
- 7
- References
- 47
- Access
- Open access
- OpenAlex
- https://openalex.org/W3005445001
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:211069171
Keywords
Odometry, Artificial intelligence, Computer science, Initialization, Point cloud
References
- Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration
- Concerning nonnegative matrices and doubly stochastic matrices
- Wide Baseline Stereo Matching based on Local, Affinely Invariant Regions
- Growing multiplex networks
- A Method for Registration of 3-D Shapes
- Community Structure in Time-Dependent, Multiscale, and Multiplex Networks
- Method for registration of 3-D shapes
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
- Calculation of the Wasserstein Distance Between Probability Distributions on the Line
- Iterative point matching for registration of free-form curves and surfaces
- Efficient variants of the ICP algorithm
- Are we ready for autonomous driving? The KITTI vision benchmark suite
- Distinctive Image Features from Scale-Invariant Keypoints
- Sinkhorn Distances: Lightspeed Computation of Optimal Transport
- Fast Point Feature Histograms (FPFH) for 3D registration
- Multidimensional binary search trees used for associative searching
- LOAM: Lidar Odometry and Mapping in Real-time
- SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter
- Multi-view 3D Object Detection Network for Autonomous Driving
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Cited by
- Vision-based Robotic Grasp Detection From Object Localization, Object Pose Estimation To Grasp Estimation: A Review.
- Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review
- PlückerNet: Learn to Register 3D Line Reconstructions¨
- Keypoint Matching for Point Cloud Registration Using Multiplex Dynamic Graph Attention Networks
- Point Transformer
- Challenging the Universal Representation of Deep Models for 3D Point Cloud Registration
- Point Transformer.