Views
No views yet
We present G2VLM, a geometry grounded vision-language model proficient in both spatial 3D reconstruction and spatial understanding tasks. For spatial reasoning questions, G2VLM can natively predict 3D geometry and employ interleaved reasoning for an answer.
1@article{hu2025g2vlmgeometrygroundedvision,
2 title={G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning},
3 author={Wenbo Hu and Jingli Lin and Yilin Long and Yunlong Ran and Lihan Jiang and Yifan Wang and Chenming Zhu and Runsen Xu and Tai Wang and Jiangmiao Pang},
4 year={2025},
5 eprint={2511.21688},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2511.21688},
9}