PaGeR：用多视图基础模型统一全景几何估计

View PDF HTML (experimental)

Abstract:Geometry estimation from perspective images has greatly advanced, maturing to the point where off-the-shelf foundation models are able to reconstruct 3D scene structure not only from multi-view imagery, but even from a single view. A natural extension is 3D reconstruction from panoramas, with the exciting prospect of recovering a full 360-degree scene from a single panoramic image. In this work, we introduce PaGeR (Panoramic Geometry Reconstruction), a framework to lift powerful 3D foundation models designed for perspective imagery to the panorama domain. Our strategy is to start from a pre-trained transformer for 3D reconstruction and turn it into a unified high-performance model that predicts scale-invariant depth, metric depth, surface normals, and sky masks from both perspective and omnidirectional images, in a single forward pass. By keeping architectural changes to a minimum and mixing perspective and panoramic images during training, PaGeR retains the rich 3D prior of the underlying foundation model while learning to also estimate geometrically consistent 360-degree scenes from single panoramas. We extensively test our method in both indoor and outdoor environments and find that it delivers state-of-the-art performance and excellent zero-shot performance across a wide range of scenes. Code, data and models are available $\href{this https URL}{\text{here}}$.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2605.26368 [cs.CV]
	(or arXiv:2605.26368v3 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2605.26368 arXiv-issued DOI via DataCite

Submission history

From: Vukasin Bozic [view email]
[v1] Mon, 25 May 2026 22:32:42 UTC (42,439 KB)
[v2] Wed, 27 May 2026 12:32:56 UTC (42,439 KB)
[v3] Tue, 10 Nov 2026 16:29:03 UTC (32,849 KB)