Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama
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_ | 1866915961807831040 |
|---|---|
| author | Li, Zhijun Su, Yongxin Yang, Di Wang, Jichao Xing, Zheyuan Wang, Qian Yao, Maoqing |
| author_facet | Li, Zhijun Su, Yongxin Yang, Di Wang, Jichao Xing, Zheyuan Wang, Qian Yao, Maoqing |
| contents | We present Genie Sim PanoRecon, a feed-forward Gaussian-splatting pipeline that delivers high-fidelity, low-cost 3D scenes for robotic manipulation simulation. The panorama input is decomposed into six non-overlapping cube-map faces, processed in parallel, and seamlessly reassembled. To guarantee geometric consistency across views, we devise a depth-aware fusion strategy coupled with a training-free depth-injection module that steers the monocular feed-forward network to generate coherent 3D Gaussians. The whole system reconstructs photo-realistic scenes in seconds and has been integrated into Genie Sim - a LLM-driven simulation platform for embodied synthetic data generation and evaluation - to provide scalable backgrounds for manipulation tasks. For code details, please refer to: https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07105 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama Li, Zhijun Su, Yongxin Yang, Di Wang, Jichao Xing, Zheyuan Wang, Qian Yao, Maoqing Robotics We present Genie Sim PanoRecon, a feed-forward Gaussian-splatting pipeline that delivers high-fidelity, low-cost 3D scenes for robotic manipulation simulation. The panorama input is decomposed into six non-overlapping cube-map faces, processed in parallel, and seamlessly reassembled. To guarantee geometric consistency across views, we devise a depth-aware fusion strategy coupled with a training-free depth-injection module that steers the monocular feed-forward network to generate coherent 3D Gaussians. The whole system reconstructs photo-realistic scenes in seconds and has been integrated into Genie Sim - a LLM-driven simulation platform for embodied synthetic data generation and evaluation - to provide scalable backgrounds for manipulation tasks. For code details, please refer to: https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world. |
| title | Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.07105 |