| Paper | Code | CIDEr | ModelName | ReleaseDate |
|---|---|---|---|---|
| GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models | ✓ Link | 96.3 | Qwen2-VL-7B (GPT4Scene)-HDM | 2025-01-02 |
| GenSplat: Bridging the Generalization Gap in 3DGS Language Comprehension | ✓ Link | 95.1 | GenSplat (extra data) | 2026-06-03 |
| 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer | ✓ Link | 92.6 | 3D-LLaVA | 2025-01-02 |
| Unifying 2D and 3D Vision-Language Understanding | ✓ Link | 78.5 | UniVLG | 2025-03-13 |
| Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding | ✓ Link | 73.2 | Lexicon3D (DINOv2) | 2024-09-05 |
| Situational Awareness Matters in 3D Vision Language Reasoning | ✓ Link | 68.8 | Situation3D | 2024-06-11 |