3D Object Classification
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
Papers
Showing 1–10 of 93 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Ours | Classification Accuracy | 93.6 | — | Unverified |
| 2 | G3DNet-18 MLP, Fine-Tuned, Vote | Classification Accuracy | 91.7 | — | Unverified |
| 3 | CrossMoCo | Classification Accuracy | 91.49 | — | Unverified |
| 4 | O-CNN(6) | Classification Accuracy | 89.9 | — | Unverified |
| 5 | 3D-PointCapsNet | Classification Accuracy | 89.3 | — | Unverified |
| 6 | Spherical Kernel | Classification Accuracy | 89.3 | — | Unverified |
| 7 | ECC (12 votes) | Classification Accuracy | 83.2 | — | Unverified |