用真实全景图像生成无缝360°画面，解决双鱼眼镜头缺陷。
Seam360GS: Seamless 360° Gaussian Splatting from Real-World Omnidirectional Images
- 将双鱼眼相机模型融入高斯点云渲染，联合优化参数与镜头畸变。
- 在真实数据集上实现无缝渲染，即使输入图像有畸变和间隙。
- 适合虚拟现实、自动驾驶等需要高质量全景重建的场景。
360°视觉内容在YouTube等平台广泛传播，在虚拟现实、机器人和自动驾驶中扮演核心角色。然而，消费级双鱼眼系统因镜头分离和角度畸变，始终产生不完美的全景图。本文提出一种新型标定框架，将双鱼眼相机模型引入3D高斯点云渲染流程。该方法不仅模拟双鱼眼相机产生的真实视觉瑕疵，还实现无缝360°图像合成。通过联合优化3D高斯参数与模拟镜头间隙和角度畸变的标定变量，本框架可将有缺陷的全景输入转化为无瑕疵的新视角合成结果。在真实数据集上的大量实验表明，该方法即使面对不完美输入仍能生成无缝渲染效果，并优于现有360°渲染模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。