paper-with-me

ScanObjectNN

홈페이지 · 논문 337편

ScanObjectNN is a newly published real-world dataset comprising of 2902 3D objects in 15 categories. It is a challenging point cloud classification datasets due to the background, missing parts and deformations. Source: A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition Image Source: https://hkust-vgd.github.io/scanobjectnn/

3DPoint cloud

벤치마크

3D Point Cloud Classification on ScanObjectNN 결과 231개

Supervised Only 3D Point Cloud Classification on ScanObjectNN 결과 36개

Zero-Shot Transfer 3D Point Cloud Classification on ScanObjectNN 결과 30개

Training-free 3D Point Cloud Classification on ScanObjectNN 결과 6개

3D Point Cloud Linear Classification on ScanObjectNN 결과 4개

Few-Shot Point Cloud Classification on ScanObjectNN 결과 1개