{"slug": "unified-panoramic-geometry-estimation-via-multi-view-foundation-models", "title": "Unified Panoramic Geometry Estimation via Multi-View Foundation Models", "summary": "Researchers have developed PaGeR, a framework that adapts existing 3D foundation models designed for perspective images to reconstruct full 360-degree scenes from single panoramic images. The model predicts scale-invariant depth, metric depth, surface normals, and sky masks from both perspective and omnidirectional images in a single forward pass. PaGeR achieves state-of-the-art performance and strong zero-shot generalization across diverse indoor and outdoor environments.", "body_md": "arXiv:2605.26368v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/unified-panoramic-geometry-estimation-via-multi-view-foundation-models", "canonical_source": "https://arxiv.org/abs/2605.26368", "published_at": "2026-05-27 04:00:00+00:00", "updated_at": "2026-05-27 04:28:03.665306+00:00", "lang": "en", "topics": ["computer-vision", "artificial-intelligence", "machine-learning", "neural-networks", "ai-research"], "entities": ["PaGeR", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/unified-panoramic-geometry-estimation-via-multi-view-foundation-models", "markdown": "https://wpnews.pro/news/unified-panoramic-geometry-estimation-via-multi-view-foundation-models.md", "text": "https://wpnews.pro/news/unified-panoramic-geometry-estimation-via-multi-view-foundation-models.txt", "jsonld": "https://wpnews.pro/news/unified-panoramic-geometry-estimation-via-multi-view-foundation-models.jsonld"}}