Gimbal360: Differentiable Auto-Leveling for Canonicalized $360^\circ$ Panoramic Image Completion

TL;DR

Gimbal360 is a novel framework that improves 360-degree panoramic image completion by explicitly handling geometric and topological challenges, using differentiable auto-leveling and topological equivariance.

Contribution

It introduces a Canonical Viewing Space, a Differentiable Auto-Leveling module, and topological equivariance to enhance panoramic completion without camera parameters.

Findings

Achieves state-of-the-art performance in 360° scene completion.

Effectively stabilizes feature orientation without camera parameters.

Handles topological boundary conditions in panoramic generation.

Abstract

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.