OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915839012241408 |
|---|---|
| author | Liu, Zixian Chen, Zhaoxi Pan, Liang Liu, Ziwei |
| author_facet | Liu, Zixian Chen, Zhaoxi Pan, Liang Liu, Ziwei |
| contents | In recent years, researchers have increasingly been interested in how to enable Multimodal Large Language Models (MLLM) to possess spatial understanding and reasoning capabilities. However, most existing methods overlook the importance of the ability to continuously work in an ever-changing world, and lack the possibility of deployment on embodied systems in real-world environments. In this work, we introduce OnlineSI, a framework that can continuously improve its spatial understanding of its surroundings given a video stream. Our core idea is to maintain a finite spatial memory to retain past observations, ensuring the size of the spatial memory does not increase as the input accumulates. We further integrate 3D point cloud information with semantic information, helping MLLM to better locate and identify objects in the scene. To evaluate our method, we introduce the Fuzzy $F_1$-Score to mitigate ambiguity, and test our method on two representative datasets. Experiments demonstrate the effectiveness of our method, paving the way towards real-world embodied systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16538 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding Liu, Zixian Chen, Zhaoxi Pan, Liang Liu, Ziwei Computer Vision and Pattern Recognition In recent years, researchers have increasingly been interested in how to enable Multimodal Large Language Models (MLLM) to possess spatial understanding and reasoning capabilities. However, most existing methods overlook the importance of the ability to continuously work in an ever-changing world, and lack the possibility of deployment on embodied systems in real-world environments. In this work, we introduce OnlineSI, a framework that can continuously improve its spatial understanding of its surroundings given a video stream. Our core idea is to maintain a finite spatial memory to retain past observations, ensuring the size of the spatial memory does not increase as the input accumulates. We further integrate 3D point cloud information with semantic information, helping MLLM to better locate and identify objects in the scene. To evaluate our method, we introduce the Fuzzy $F_1$-Score to mitigate ambiguity, and test our method on two representative datasets. Experiments demonstrate the effectiveness of our method, paving the way towards real-world embodied systems. |
| title | OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.16538 |