SKD: Unsupervised Keypoint Detecting for Point Clouds using Embedded Saliency Estimation
Explore this paper's citation graph
Summary
A novel keypoint detector that uses saliency to determine the best candidates from point clouds and combines the saliency, the feature signal and geometric information from the point cloud to allow the network to select good keypoint candidates.
- Type
- article
- Published
- 2019-12-10
- Cited by
- 2
- References
- 42
- Access
- Open access
- OpenAlex
- https://openalex.org/W2996113968
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:209202798
Keywords
Point cloud, Artificial intelligence, Point (geometry), Estimation, Pattern recognition (psychology)
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- TILDE: A Temporally Invariant Learned DEtector
- Intrinsic shape signatures: A shape descriptor for 3D object recognition
- A new method for gray-level picture thresholding using the entropy of the histogram
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
- Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes
- A Combined Corner and Edge Detector
- Vision meets robotics: The KITTI dataset
- Unique shape context for 3d data description
- Distinctive Image Features from Scale-Invariant Keypoints
- Fast Point Feature Histograms (FPFH) for 3D registration
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection
- 1 year, 1000 km: The Oxford RobotCar dataset
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Learning Compact Geometric Features
- Frustum PointNets for 3D Object Detection from RGB-D Data
Cited by
Related papers
- SKD: Keypoint Detection for Point Clouds Using Saliency Estimation
- GraB: Visual Saliency via Novel Graph Model and Background Priors
- Saliency and co-saliency detection by low-rank multiscale fusion
- Saliency detection using boundary information
- A video saliency detection method based on spatial and motion information
- Co-saliency detection via similarity-based saliency propagation
- Depth-aware saliency detection using discriminative saliency fusion