# Seam360GS: Seamless 360{\deg} Gaussian Splatting from Real-World Omnidirectional Images

## TL;DR

Seam360GS introduces a calibration framework that integrates dual-fisheye camera modeling into 3D Gaussian splatting, enabling seamless 360-degree image synthesis from imperfect real-world omnidirectional images, with improved rendering quality.

## Contribution

The paper presents a novel calibration method that models dual-fisheye distortions within the Gaussian splatting pipeline for seamless 360-degree view synthesis.

## Key findings

- Produces seamless 360-degree renderings from imperfect images
- Outperforms existing 360-degree rendering models
- Effectively models lens artifacts and distortions

## Abstract

360-degree visual content is widely shared on platforms such as YouTube and plays a central role in virtual reality, robotics, and autonomous navigation. However, consumer-grade dual-fisheye systems consistently yield imperfect panoramas due to inherent lens separation and angular distortions. In this work, we introduce a novel calibration framework that incorporates a dual-fisheye camera model into the 3D Gaussian splatting pipeline. Our approach not only simulates the realistic visual artifacts produced by dual-fisheye cameras but also enables the synthesis of seamlessly rendered 360-degree images. By jointly optimizing 3D Gaussian parameters alongside calibration variables that emulate lens gaps and angular distortions, our framework transforms imperfect omnidirectional inputs into flawless novel view synthesis. Extensive evaluations on real-world datasets confirm that our method produces seamless renderings-even from imperfect images-and outperforms existing 360-degree rendering models.