FIORD：一个用于三维场景重建与基准测试的鱼眼室内外数据集，配备激光雷达真值
FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking
AI总结：
本文提出FIORD数据集，利用双200度鱼眼镜头采集5个室内和5个室外场景的360度覆盖图像，并提供激光雷达稠密点云作为几何真值，以支持在遮挡和反射等挑战性条件下的三维场景重建与新视角合成基准测试。
摘要：
大规模三维场景重建和新视角合成方法的发展大多依赖于包含窄视场（FoV）透视图像的数据集。虽然这些数据集对小规模场景有效，但它们需要大量图像集和广泛的结构从运动（SfM）处理，限制了可扩展性。为了解决这一问题，我们引入了一个专门为场景重建任务定制的鱼眼图像数据集。通过使用双200度鱼眼镜头，我们的数据集提供了5个室内和5个室外场景的完整360度覆盖。每个场景都具有稀疏的SfM点云和精确的激光雷达导出的稠密点云，可用作几何真值，从而能够在遮挡和反射等具有挑战性的条件下进行稳健的基准测试。虽然基线实验侧重于普通的Gaussian Splatting和基于NeRF的Nerfacto方法，但该数据集支持场景重建、新视角合成和基于图像的渲染的多种方法。
英文摘要：
The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require large image sets and extensive structure-from-motion (SfM) processing, limiting scalability. To address this, we introduce a fisheye image dataset tailored for scene reconstruction tasks. Using dual 200-degree fisheye lenses, our dataset provides full 360-degree coverage of 5 indoor and 5 outdoor scenes. Each scene has sparse SfM point clouds and precise LIDAR-derived dense point clouds that can be used as geometric ground-truth, enabling robust benchmarking under challenging conditions such as occlusions and reflections. While the baseline experiments focus on vanilla Gaussian Splatting and NeRF based Nerfacto methods, the dataset supports diverse approaches for scene reconstruction, novel view synthesis, and image-based rendering.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
