Li, JunboHahlbohm, FlorianScholz, TimonEisemann, MartinTauscher, Jan-PhilippMagnor, MarcusWang, BeibeiWilkie, Alexander2025-06-202025-06-2020251467-8659https://doi.org/10.1111/cgf.70171https://diglib.eg.org/handle/10.1111/cgf70171In this paper we propose SPaGS, a high-quality, real-time free-viewpoint rendering approach from 360-degree panoramic images. While existing methods building on Neural Radiance Fields or 3D Gaussian Splatting have difficulties to achieve real-time frame rates and high-quality results at the same time, SPaGS combines the advantages of an explicit 3D Gaussian-based scene representation and ray casting-based rendering to attain fast and accurate results. Central to our new approach is the exact calculation of axis-aligned bounding boxes for spherical images that significantly accelerates omnidirectional ray casting of 3D Gaussians. We also present a new dataset consisting of ten real-world scenes recorded with a drone that incorporates both calibrated 360-degree panoramic images as well as perspective images captured simultaneously, i.e., with the same flight trajectory. Our evaluation on this new dataset as well as established benchmarks demonstrates that SPaGS excels over state-of-the-art methods in terms of both rendering quality and speed.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Rendering; Point-based models; Rasterization; Machine learning approachesComputing methodologies → RenderingPointbased modelsRasterizationMachine learning approaches10.1111/cgf.7017111 pages