论文/arXiv 2610.21297·13 天前

GeoPano：迈向从单张全景图进行几何精确的3D重建

GeoPano面向单张全景图3D重建，通过全景感知注意力与混合监督恢复一致点云，并在实验中优于既有SOTA。

AI 整理

• 感知与导航

原文链接：GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama（arXiv 2610.21297 · 发布日期：2026-10-15）

GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama

GeoPano面向单张全景图3D重建，通过全景感知注意力与混合监督恢复一致点云，并在实验中优于既有SOTA。

核心要点

• 全景3D重建有助于360度场景几何恢复，但ERP图像存在球面畸变。
• 全景感知注意力聚合器利用内在球面几何，引导跨视图交互。
• 混合监督同时约束透视空间局部细节与球面空间全局结构一致性。
• 实验显示其在重建精度、几何一致性和视觉保真度上显著优于既有SOTA。

验证范围与局限：验证范围为单张全景图的3D重建实验，摘要未说明具体数据集或真实/仿真场景。

英文摘要 (Abstract)

Panoramic 3D reconstruction enables the holistic recovery of complete 360 $^\circ$ scene geometry, offering significant benefits for robotics and AR/VR applications. However, directly estimating geometry from ERP images is inherently challenged by spherical distortions. To reduce spherical projection distortions, a common strategy is to decompose panoramas into distortion-free perspective views, but independently processing these views often introduces cross-view geometric inconsistencies. To address these challenges, we introduce GeoPano, a feed-forward framework for single-view panoramic 3D reconstruction that recovers a geometrically accurate and consistent point cloud from a single panorama. Our approach is driven by two key innovations: First, we propose a panoramic-aware attention aggregator, featuring a streamlined attention architecture equipped with a novel Pano-Attention mechanism, which explicitly exploits the intrinsic spherical geometry of the panorama to guide cross-view interactions, thereby suppressing geometric inconsistencies. Furthermore, we formulate a hybrid supervision strategy to jointly enforce fine-grained local details in perspective space and global structural coherence in spherical space. Experiments demonstrate that our method significantly outperforms previous SOTA approaches in reconstruction accuracy, geometric consistency, and visual fidelity.

作者：Jing OU, Zidong Cao, Liaoyuan Fan, Zhuoxiao Li, Shuai Zhang, Yinrui Ren, Dongli Wu, Haoang Li, Hui Xiong, Wufan Zhao

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.21297：GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single Panorama访问 2026-10-21