ModelNet

홈페이지 · 논문 1,406편

The ModelNet40 dataset contains synthetic object point clouds. As the most widely used benchmark for point cloud analysis, ModelNet40 is popular because of its various categories, clean shapes, well-constructed dataset, etc. The original ModelNet40 consists of 12,311 CAD-generated meshes in 40 categories (such as airplane, car, plant, lamp), of which 9,843 are used for training while the rest 2,468 are reserved for testing. The corresponding point cloud data points are uniformly sampled from the mesh surfaces, and then further preprocessed by moving to the origin and scaling into a unit sphere. Source: Geometric Feedback Network for Point Cloud Classification

3DPoint cloud Chinese

벤치마크

3D Point Cloud Classification on ModelNet40 결과 333개

Few-Shot 3D Point Cloud Classification on ModelNet40 10-way (10-shot) 결과 93개

Few-Shot 3D Point Cloud Classification on ModelNet40 10-way (20-shot) 결과 93개

Few-Shot 3D Point Cloud Classification on ModelNet40 5-way (10-shot) 결과 90개

Few-Shot 3D Point Cloud Classification on ModelNet40 5-way (20-shot) 결과 90개

Zero-Shot Transfer 3D Point Cloud Classification on ModelNet40 결과 48개

3D Object Classification on ModelNet40 결과 42개

Generative 3D Object Classification on ModelNet40 결과 42개

3D Object Classification on ModelNet10 결과 24개

3D Point Cloud Linear Classification on ModelNet40 결과 20개

Zero-Shot Transfer 3D Point Cloud Classification on ModelNet10 결과 12개

Training-free 3D Point Cloud Classification on ModelNet40 결과 7개

3D Object Recognition on ModelNet40 결과 6개

3D Object Retrieval on ModelNet40 결과 1개

Few-Shot Point Cloud Classification on ModelNet40 결과 1개