Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2603.11911 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914533158682624 |
|---|---|
| author | InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Xiang, Xiaojun Zhang, Xiaoyu Liu, Xianbin Wang, Yifu Chen, Yipeng Le, Zhewen Ye, Zhichao Zhao, Ziqiang |
| author_facet | InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Xiang, Xiaojun Zhang, Xiaoyu Liu, Xianbin Wang, Yifu Chen, Yipeng Le, Zhewen Ye, Zhichao Zhao, Ziqiang |
| contents | We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11911 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Xiang, Xiaojun Zhang, Xiaoyu Liu, Xianbin Wang, Yifu Chen, Yipeng Le, Zhewen Ye, Zhichao Zhao, Ziqiang Computer Vision and Pattern Recognition We present InSpatio-WorldFM, an open-source real-time frame model for spatial intelligence. Unlike video-based world models that rely on sequential frame generation and incur substantial latency due to window-level processing, InSpatio-WorldFM adopts a frame-based paradigm that generates each frame independently, enabling low-latency real-time spatial inference. By enforcing multi-view spatial consistency through explicit 3D anchors and implicit spatial memory, the model preserves global scene geometry while maintaining fine-grained visual details across viewpoint changes. We further introduce a progressive three-stage training pipeline that transforms a pretrained image diffusion model into a controllable frame model and finally into a real-time generator through few-step distillation. Experimental results show that InSpatio-WorldFM achieves strong multi-view consistency while supporting interactive exploration on consumer-grade GPUs, providing an efficient alternative to traditional video-based world models for real-time world simulation. |
| title | InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.11911 |