Newest papers

OmniRay: Camera-Agnostic Monocular 3D Reconstruction with Composite Ray Fields

N. Guruprasad, Abhay Yadav, Cheng Peng, Rama Chellappa, Anand Bhattad · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31645 · cited by 0 works (OpenAlex) · open-access PDF

German

Extocular-Kameramodelle erholen 3D-Geometrie von einem einzelnen Bild in einem Pass, aber die meisten nehmen eine Pinhole-Kamera an und produzieren verzerrte Geometrie auf den breitwinkeligen Bildern, die von fisheye und Panorama-Objektiven produziert werden. Kamera-bewußte Modelle entfernen diese Annahme, indem sie ein Per-Pixel-Ray-Feld vorhersagen. Jedoch repräsentieren sie verschiedene Kameramodule mit einer einzigen festen Basis, um sowohl die Gesamtprojektion als auch ihre feineren Variationen zu erfassen. Wir argumentieren, dass die Kameramodelle als eine Hierarchie der Komplexität für die Repräsentation von Strahlen angesehen werden kann. Wir präsentieren OmniRay, ein Feed-Follow-Modell

Machine translation (Meta M2M100); the English original follows.

Abstract

Monocular models recover 3D geometry from a single image in one pass, but most assume a pinhole camera and produce distorted geometry on the wide-angle imagery produced by fisheye and panoramic lenses. Camera-aware models remove this assumption by predicting a per-pixel ray field. However, they represent different camera geometries using a single fixed basis to capture both the overall camera projection and its finer variations. We argue that camera geometry can be viewed as having a hierarchy of complexity for representing rays. We present OmniRay, a feed-forward model whose Ray Module is composed of three components: a monotone radial base that captures radially symmetric structure, a spherical-harmonic residual for smooth deviations from it, and a free-form residual for remaining local variation. These components are composed as successive rotations on the sphere, allowing the representation to accommodate diverse camera geometries. Given a single image, OmniRay predicts a ray direction and an up-to-scale radial distance for every pixel, from which a 3D point cloud is recovered without needing camera information at inference time. Extensive experiments across different camera configurations demonstrate that OmniRay establishes a new state-of-the-art in camera-agnostic monocular 3D reconstruction.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Artificial intelligence, Computer vision, Pinhole camera, Pinhole camera model, Point cloud, Projection (relational algebra)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange