ModelNet40-C

ModelNet-C

Dataset Information
Modalities
3D, Point cloud
Languages
English
Introduced
2022
License
BSD 3-Clause
Homepage
Official Website
Contents

Overview

ModelNet40-C is a comprehensive dataset to benchmark the corruption robustness of 3D point cloud recognition.

We create ModelNet40-C based on the ModelNet40 validation set with 15 corruption types and 5 severity levels for each corruption type including density, noise, and transformation corruption patterns. Our dataset contains 185,000 distinct point clouds that help provide a comprehensive picture of model robustness.

Variants: ModelNet40-C

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
3D Point Cloud Classification OmniVec OmniVec: Learning robust representations with … 2023-11-07
3D Point Cloud Classification PCT+PointCutMix-R Benchmarking Robustness of 3D Point … 2022-01-28
3D Point Cloud Classification PCT+RSMix Regularization Strategy for Point Cloud … 2021-02-03
3D Point Cloud Classification DGCNN+PointCutMix-R PointCutMix: Regularization Strategy for Point … 2021-01-05
3D Point Cloud Classification PointNet++/+PointCutMix-R PointCutMix: Regularization Strategy for Point … 2021-01-05
3D Point Cloud Classification PCT PCT: Point cloud transformer 2020-12-17
3D Point Cloud Classification PointNet++/+PointMixup PointMixup: Augmentation for Point Clouds 2020-08-14
3D Point Cloud Classification RSCNN Relation-Shape Convolutional Neural Network for … 2019-04-16
3D Point Cloud Classification DGCNN Dynamic Graph CNN for Learning … 2018-01-24
3D Point Cloud Classification PointNet++ PointNet++: Deep Hierarchical Feature Learning … 2017-06-07
3D Point Cloud Classification PointNet PointNet: Deep Learning on Point … 2016-12-02

Research Papers

Recent papers with results on this dataset:

External Links: