Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Spherical-GOF: Geometry-Aware Panoramic Gaussian Opacity Fields for 3D Scene Reconstruction

Zhe Yang, Guoqiang Zhao, Sheng Wu, Kai Luo, Kailun Yang

TL;DR

Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields, enables consistent ray-Gaussian interactions for panoramic rendering and further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work.

Abstract

Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models remains challenging, as existing formulations are designed for perspective projections and naive adaptations often introduce distortion and geometric inconsistencies. We present Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields (GOF). Unlike projection-based rasterization, Spherical-GOF performs GOF ray sampling directly on the unit sphere in spherical ray space, enabling consistent ray-Gaussian interactions for panoramic rendering. To make the spherical ray casting efficient and robust, we derive a conservative spherical bounding rule for fast ray-Gaussian culling and introduce a spherical filtering scheme that adapts Gaussian footprints to distortion-varying panoramic pixel sampling. Extensive experiments on standard panoramic benchmarks (OmniBlender and OmniPhotos) demonstrate competitive photometric quality and substantially improved geometric consistency. Compared with the strongest baseline, Spherical-GOF reduces depth reprojection error by 57% and improves cycle inlier ratio by 21%. Qualitative results show cleaner depth and more coherent normal maps, with strong robustness to global panorama rotations. We further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work, featuring UAV and quadruped platforms. The source code and the OmniRob dataset will be released at https://github.com/1170632760/Spherical-GOF.

Spherical-GOF: Geometry-Aware Panoramic Gaussian Opacity Fields for 3D Scene Reconstruction

TL;DR

Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields, enables consistent ray-Gaussian interactions for panoramic rendering and further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work.

Abstract

Omnidirectional images are increasingly used in robotics and vision due to their wide field of view. However, extending 3D Gaussian Splatting (3DGS) to panoramic camera models remains challenging, as existing formulations are designed for perspective projections and naive adaptations often introduce distortion and geometric inconsistencies. We present Spherical-GOF, an omnidirectional Gaussian rendering framework built upon Gaussian Opacity Fields (GOF). Unlike projection-based rasterization, Spherical-GOF performs GOF ray sampling directly on the unit sphere in spherical ray space, enabling consistent ray-Gaussian interactions for panoramic rendering. To make the spherical ray casting efficient and robust, we derive a conservative spherical bounding rule for fast ray-Gaussian culling and introduce a spherical filtering scheme that adapts Gaussian footprints to distortion-varying panoramic pixel sampling. Extensive experiments on standard panoramic benchmarks (OmniBlender and OmniPhotos) demonstrate competitive photometric quality and substantially improved geometric consistency. Compared with the strongest baseline, Spherical-GOF reduces depth reprojection error by 57% and improves cycle inlier ratio by 21%. Qualitative results show cleaner depth and more coherent normal maps, with strong robustness to global panorama rotations. We further validate generalization on OmniRob, a real-world robotic omnidirectional dataset introduced in this work, featuring UAV and quadruped platforms. The source code and the OmniRob dataset will be released at https://github.com/1170632760/Spherical-GOF.
Paper Structure (12 sections, 21 equations, 5 figures, 4 tables)

This paper contains 12 sections, 21 equations, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Preliminary: Classical Gaussian Splatting and Gaussian Opacity Fields
  5. Panoramic Rendering via Gaussian Opacity Field
  6. Optimization Strategies for Panoramic Rendering
  7. Panorama-Aware Geometric Losses
  8. Experiments
  9. Experimental Setup
  10. Experiment Results
  11. Implications for Embodied Intelligence
  12. Conclusion

Figures (5)

  • Figure 1: Qualitative comparison on OmniBlenderchoi2023balanced. We show RGB renderings and geometry-related outputs for representative scenes. Compared to projection-based panoramic 3DGS baselines, our method yields smoother and more structurally consistent depth, with fewer texture-aligned ripples on planar regions. Normal maps are computed from the rendered depth for visualization.
  • Figure 2: Rotation robustness under global panorama rotations. We train with canonical poses and evaluate the same scene under additional global rotations of $0^\circ$, $60^\circ$, and $90^\circ$. Each result includes a zoom-in inset from a fixed region for easier comparison. Projection-based methods (ODGS lee2024odgs and OmniGS li2025omnigs) show increasing rotation-dependent degradation, while SPaGS li2025spags and our method remain more stable under large rotations.
  • Figure 3: Qualitative ablation on OmniBlender choi2023balanced.
  • Figure 4: Qualitative results on OmniRob annular panoramas. Rows show GT, SPaGS (RGB/normal), and Ours (RGB/normal).
  • Figure 5: Mesh extraction results on OmniBlender choi2023balanced. Our method reconstructs clean surfaces with fewer holes and reduced texture-induced artifacts.