Gimbal360 Logo

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

Orange Team

Yuqin Lu Haofeng Liu Yang Zhou Jun Liang Shengfeng He Jing Li
Paper Code (Coming Soon) Dataset (Coming Soon)

TL;DR: Gimbal360 robustly canonicalizes unposed perspective images using differentiable auto-leveling, enabling structurally consistent and seamless 360° panorama generation.

Auto-Leveling: OFF ON

Input Perspective

Input

360° Panorama Generation (ERP)

Final ERP
Projected

Seam Visualization

Seam
SEAM CROP

Demo

Input Image

Input Perspective

Seamless 360° Panorama Generation

Full ERP Panorama

Interactive Viewer

Click and drag to explore

Select an Input

Click an image below to generate its panorama

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.

Methodology

Gimbal360 Architecture Diagram

Given a perspective sample from our Horizon360 Dataset, the Differentiable Auto-Leveling module predicts a rigid correspondence field to warp the perspective image into a gravity-aligned, yaw-centered Canonical Viewing Space. During Topologically Equivariant Generation, a Siamese Consistency Loss between the standard and horizontally shifted latent streams forces the network to natively respect the continuous \(S^1\) boundary.

BibTeX

@misc{orange2026gimbal360,
title={Gimbal360: Differentiable Auto-Leveling for Canonicalized 360 Panoramic Image Completion},
author={Orange Team},
year={2026},
url={https://orange-3dv-team.github.io/MoCam}
}