Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama
This provides scalable backgrounds for manipulation tasks in an LLM-driven simulation platform, though it appears incremental as it builds on existing Gaussian-splatting and cube-map decomposition techniques.
The paper tackles the problem of generating immersive 3D scenes from single-view panoramas for robotic manipulation simulation, achieving photo-realistic reconstruction in seconds with a feed-forward Gaussian-splatting pipeline.
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.