Poster
in
Workshop: Geometry-grounded Representation Learning and Generative Modeling
Geometry Fidelity for Spherical Images
Anders Christensen · Nooshin Mojab · Khushman Patel · Karan Ahuja · Zeynep Akata · Ole Winther · Mar Gonzalez-Franco · Andrea Colaco
Keywords: [ fov ] [ metric ] [ fidelity ] [ vr ] [ field-of-view ] [ spherical image ]
Spherical or omni-directional images offer an immersive visual format appealing to a wide range of computer vision applications. However, geometric properties of spherical images pose a major challenge for models and metrics designed for ordinary 2D images. We show that direct application of Fréchet Inception Distance (FID) is insufficient for quantifying geometric fidelity in spherical images. To remedy this, we introduce Omnidirectional FID (OmniFID), an extension of FID, which additionally captures field-of-view requirements of the spherical format.