Diffusion models excel at 2D outpainting, but extending them to $360^\circ$ panoramic completion from unposed perspective images is challenging due to the geometric and topological mismatch between perspective projections and spherical panoramas. We present Gimbal360, a principled framework that explicitly bridges perspective observations and spherical panoramas. We introduce a Canonical Viewing Space that regularizes projective geometry and provides a consistent intermediate representation between the two domains. To anchor in-the-wild inputs to this space, we propose a Differentiable Auto-Leveling module that stabilizes feature orientation without requiring camera parameters at inference. Panoramic generation also introduces a topological challenge. Standard generative architectures assume a bounded Euclidean image plane, while Equirectangular Projection (ERP) panoramas exhibit intrinsic $S^1$ periodicity. Euclidean operations therefore break boundary continuity. We address this mismatch by enforcing topological equivariance in the latent space to preserve seamless periodic structure. To support this formulation, we introduce Horizon360, a curated large-scale dataset of gravity-aligned panoramic environments. Extensive experiments show that explicitly standardizing geometric and topological priors enables Gimbal360 to achieve state-of-the-art performance in structurally consistent $360^\circ$ scene completion.

翻译：扩散模型在二维外推任务中表现优异，但将其扩展至基于无位姿透视图像的全景补全面临挑战，这源于透视投影与球面全景之间的几何与拓扑不匹配。本文提出Gimbal360，一个明确桥接透视观测与球面全景的规范化框架。我们引入规范观测空间，该空间正则化投影几何并提供了两个域之间的一致性中间表示。为将野外输入锚定至此空间，我们提出可微分自动水平校正模块，无需推理时相机参数即可稳定特征朝向。全景生成还引入了拓扑挑战：标准生成架构假设有界欧几里得图像平面，而等距柱状投影全景图呈现固有的$S^1$周期性，因此欧几里得运算会破坏边界连续性。我们通过在隐空间中强制拓扑等变性以保持无缝周期结构来解决此失配问题。为支撑该公式，我们引入Horizon360，一个经梳理的、对齐重力方向的全景环境大规模数据集。大量实验表明，明确标准化几何与拓扑先验使Gimbal360在结构一致的$360^\circ$场景补全中达到最优性能。