| Paper | Code | Acc@0.25 | Acc@0.5 | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Unifying 2D and 3D Vision-Language Understanding | ✓ Link | 63.5 | 56.4 | UniVLG | 2025-03-13 |
| Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding | ✓ Link | 62.8 | Qwen-3D-7B | 2026-08-04 | |
| GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models | ✓ Link | 62.6 | Qwen2-VL-7B (GPT4Scene)-HDM | 2025-01-02 | |
| G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding | 56.9 | 45.58 | G3-LQ (Two-Stage) | 2024-06-17 | |
| Viewpoint-Aware Visual Grounding in 3D Scenes | 55.65 | 43.29 | VPP-Net (extra data) | 2024-06-17 | |
| 3D-LLM: Injecting the 3D World into Large Language Models | ✓ Link | 30.3 | 3D-LLM (BLIP2-flant5) | 2023-07-24 | |
| Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding | ✓ Link | 55.3 | Qwen-3D-3B | 2026-08-04 |