单张全景图秒级生成逼真3D场景，用于机器人模拟。
Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama
- 将全景图切分为六面立方图，并行处理后无缝拼合。
- 通过深度感知融合与免训练深度注入，实现跨视角几何一致。
- 已集成至大模型驱动的仿真平台，支持大规模任务背景生成。
我们提出 Genie Sim PanoRecon，一种前馈式高斯溅射管线，可高效生成高质量、低成本的3D场景，用于机器人操作仿真。输入全景图被分解为六个无重叠的立方图面，进行并行处理后无缝重组。为保证多视角间的几何一致性，我们设计了一种深度感知融合策略，并引入无需训练的深度注入模块，引导单目前馈网络生成连贯的3D高斯分布。整个系统可在数秒内重建照片级真实感场景，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，提供可扩展的操作任务背景。代码详情请见：https://github.com/AgibotTech/genie_sim/tree/main/source/geniesim_world。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。