3D Object Recognition on 3D Objects
61.33Recognition AccuracyGPT-4V
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4VInput=Single-view Img.2025.12 | 61.33 | |
| Lemon-7BTrainable Params=7.63B, Input=3D Point Cloud2025.12 | 59.2 | |
| Qwen2.5-VL-7BTrainable Params=7.61B, Input=Single-view Img.2025.12 | 58.72 | |
| GreenPLMTrainable Params=3.8B, Input=3D Point Cloud2025.12 | 54.65 | |
| PointLLM-13BTrainable Params=13.01B, Input=3D Point Cloud2025.12 | 54.32 | |
| ShapeLLM-13BTrainable Params=13.04B, Input=3D Point Cloud2025.12 | 54.15 | |
| ShapeLLM-7BTrainable Params=7.04B, Input=3D Point Cloud2025.12 | 54.09 | |
| MiniGPT-3DTrainable Params=2.7B, Input=3D Point Cloud2025.12 | 53.52 | |
| PointLLM-7BTrainable Params=7.01B, Input=3D Point Cloud2025.12 | 53.49 | |
| LLaVA-1.5-13BTrainable Params=13.03B, Input=Single-view Img.2025.12 | 36.04 | |
| 3D-LLMInput=Multi-view Img.2025.12 | 22.89 |