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.
Figures & tables
Fig. 1: Overview of Genie Sim PanoRecon pipeline. An input panorama is processed to extract global structural depth (via DA360) and high-resolution local depth details (via DepthPro). These depths are aligned and fused using an inverse-depth Laplacian pyramid. The fused panoramic depth and RGB are then projected into six cubemap faces, serving as geometric constraints to drive a training-free, depth-guided feed-forward Gaussian generation (via SHARP). Finally, the individual faces are merged to form a globally consistent 3D scene.
Fig. 2: PanoRecon Overview. Top: Input single-view panorama. Bottom: Decomposed cubemap faces and the final reconstructed 3D Gaussian scene.
Fig. 3: Novel View Synthesis Comparison.
Fig. 4: Panoramic Depth Comparison. DA360 preserves global structure but lacks detail, whereas DepthPro offers sharp details with scale inconsistency. Our fusion achieves both accurate global constraints and sharp local boundaries.
Fig. 5: Effect of Anti-aliasing. Applying anti-aliasing during cubemap projection mitigates stair-step artifacts and boundary noise, enabling accurate feed-forward Gaussian initialization.
Fig. 6: Preservation of Fine-Grained Details. By integrating high-frequency depth cues, our pipeline effectively captures intricate local structures. Compared to relying solely on global depth priors, our proposed method yields significantly sharper object boundaries and preserves tiny geometric details in the reconstructed 3D scene.
Fig. 7: Accurate Spatial Geometry. The reconstructed 3D Gaussian scenes exhibit highly coherent spatial structures and accurate geometric layouts derived from single-view panoramas (e.g., DiT360 generated inputs). The preserved global consistency and minimal structural distortion make these scenes highly suitable for serving as robust background assets in indoor robotic manipulation simulations.