3DPoint cloud

ScanObjectNN

Introduced in Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data2018

About this Dataset

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/

Source: Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

Dataset Variants

ScanObjectNN

Papers1

Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data

This paper introduces ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data, and proposes new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background.

Tasks

EDIT

3D Point Cloud Classification Zero-shot 3D Point Cloud Classification 3D Point Cloud Data Augmentation Zero-Shot Transfer 3D Point Cloud Classification Few-Shot Point Cloud Classification 3D Point Cloud Linear Classification Training-free 3D Point Cloud Classification 3D Parameter-Efficient Fine-Tuning for Classification Zero-shot 3D Point Cloud Classificationclassification Supervised Only 3D Point Cloud Classification

Similar Datasets

ShapeNet

BSDS500

BP4D

Statistics

Papers

1

Tasks

192

Introduced

2018

License

Custom (research-only)

Modalities

3DPoint cloud