3D Question Answering 3D Qa On 3D Mm Vet
Metrics
Overall Accuracy
Results
Performance results of various models on this benchmark
Model Name | Overall Accuracy | Paper Title | Repository |
|---|---|---|---|
| Point-Bind & Point-LLM | 23.5 | Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following | |
| ShapeLLM-13B | 53.1 | ShapeLLM: Universal 3D Object Understanding for Embodied Interaction | |
| ShapeLLM-7B | 47.4 | ShapeLLM: Universal 3D Object Understanding for Embodied Interaction | |
| PointLLM-13B v1.2 | 46.6 | PointLLM: Empowering Large Language Models to Understand Point Clouds | |
| PointLLM-7B v1.2 | 41.2 | PointLLM: Empowering Large Language Models to Understand Point Clouds |
0 of 5 row(s) selected.