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.

翻译：我们提出了Genie Sim PanoRecon，一种前馈高斯泼溅流水线，旨在为机器人操作仿真生成高保真、低成本的3D场景。全景图输入被分解为六个互不重叠的立方体贴图面，进行并行处理，并实现无缝重组。为确保视图间的几何一致性，我们设计了一种深度感知融合策略，并搭配一个无需训练的深度注入模块，该模块引导单目前馈网络生成连贯的3D高斯体。整个系统可在数秒内重建出照片级真实的场景，并已集成至Genie Sim（一个由大语言模型驱动的仿真平台，用于具身合成数据生成与评估），为操作任务提供可扩展的背景。有关代码详情，请参阅：https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world。