A Dynamic Reduction Network for Point Clouds
Classifying whole images is a classic problem in machine learning, and graph neural networks are a powerful methodology to learn highly irregular geometries. It is often the case that certain parts of a point cloud are more important than others when determining overall classification. On graph structures this started by pooling information at the end of convolutional filters, and has evolved to a variety of staged pooling techniques on static graphs. In this paper, a dynamic graph formulation of pooling is introduced that removes the need for predetermined graph structure. It achieves this by dynamically learning the most important relationships between data via an intermediate clustering. The network architecture yields interesting results considering representation size and efficiency. It also adapts easily to a large number of tasks from image classification to energy regression in high energy particle physics.
Code (1)
Tasks
ClusteringGeneral Classificationimage-classificationImage ClassificationSuperpixel Image ClassificationSimilar Papers 제목 키워드 기반
DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds
Existing post-decoding quality enhancement methods for point clouds are designed for static data and typically process each frame independently. As a result, they cannot effectively exploit the spatiotemporal correlation…
Point CloudsSTQE: Spatial-Temporal Attribute Quality Enhancement for G-PCC Compressed Dynamic Point Clouds
Very few studies have addressed quality enhancement for compressed dynamic point clouds. In particular, the effective exploitation of spatial-temporal correlations between point cloud frames remains largely unexplored. A…
Point CloudsCylindrical coordinates for LiDAR point cloud compression
We present an efficient voxelization method to encode the geometry and attributes of 3D point clouds obtained from autonomous vehicles. Due to the circular scanning trajectory of sensors, the geometry of LiDAR point clou…
AttributeAutonomous VehiclesEfficient Urban-scale Point Clouds Segmentation with BEV Projection
Point clouds analysis has grasped researchers' eyes in recent years, while 3D semantic segmentation remains a problem. Most deep point clouds models directly conduct learning on 3D point clouds, which will suffer from th…
3D Semantic SegmentationSegmentationSemantic SegmentationMotion Estimation Techniques for Volumetric Video Attribute Compression
Point cloud compression relies on techniques to compress both geometry and attributes. Motion-based approaches for dynamic solid point cloud geometry compression within the geometry-based point cloud compression (G-PCC) …
Point Clouds