Generative 3D Object Classification
The task of generative 3D object classification involves prompting the model to generate the object type from its point cloud, distinguishing it from discriminative models that directly classify objects based on probability comparisons.
Papers
Showing 1–5 of 5 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | MiniGPT-3D | ModelNet40 (Average) | 60.86 | — | Unverified |
| 2 | ShapeLLM-7B | ModelNet40 (Average) | 53.08 | — | Unverified |
| 3 | ShapeLLM-13B | ModelNet40 (Average) | 52.96 | — | Unverified |
| 4 | PointLLM-13B v1.2 | ModelNet40 (Average) | 52.78 | — | Unverified |
| 5 | PointLLM-7B v1.2 | ModelNet40 (Average) | 52.63 | — | Unverified |
| 6 | Point-Bind LLM | ModelNet40 (Average) | 45.81 | — | Unverified |