Training Free 3D Point Cloud Classification
Metrics
Accuracy (%)
Need 3D Data?
Results
Performance results of various models on this benchmark
Model Name | Accuracy (%) | Need 3D Data? | Paper Title | Repository |
|---|---|---|---|---|
| CLIP2Point | 49.4 | Yes | CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training | |
| PointCLIP V2 | 64.2 | No | PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning | |
| Point-NN | 82.6 | Yes | Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis | |
| Point-GN | 85.3 | Yes | Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification | - |
| CALIP | 21.5 | No | CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention | |
| PointCLIP | 20.2 | No | PointCLIP: Point Cloud Understanding by CLIP | |
| ULIP | 60.4 | Yes | ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding |
0 of 7 row(s) selected.