3D Object Classification

11 benchmarks93 papers

3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.

Image: Sedaghat et al

Benchmarks

3D Object Classification on ModelNet40

Classification AccuracyModelNet40 (Average)ModelNet40 (I)ModelNet40 (C)

3D Object Classification on Objaverse

Objaverse (Average)Objaverse (I)Objaverse (C)

3D Object Classification on ModelNet10

Accuracy

3D Object Classification on 3R-Scan

Top-10 AccuracyTop-5 Accuracy

3D Object Classification on Remote Flash LiDAR Vehicles Dataset

mean average precision