首个全景鱼眼图像数据集，含激光雷达真实几何信息，助力3D重建与视角合成。
FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking
- 采用双200度鱼眼镜头，实现360度全景覆盖的室内室外场景采集。
- 每场景配备稀疏SfM点云与高精度激光雷达密集点云作为真实几何参考。
- 支持多种重建方法评测，尤其适合有遮挡、反光等复杂场景研究。
大规模3D场景重建与新视角合成方法主要依赖窄视场（FoV）的透视图像数据集。尽管对小场景有效，但需大量图像和复杂的结构从运动（SfM）处理，限制了可扩展性。为此，我们提出一个专为场景重建设计的鱼眼图像数据集。使用两个200度鱼眼镜头，数据集覆盖5个室内与5个室外场景，提供完整的360度视野。每个场景均配有稀疏的SfM点云和由激光雷达生成的精确密集点云，可作为几何真值，支持在遮挡、反射等挑战性条件下的可靠基准测试。基线实验聚焦于传统的高斯点阵与基于NeRF的Nerfacto方法，但该数据集支持多样化的场景重建、新视角合成与基于图像的渲染方法。
原文摘要 · Abstract (English)
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.
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。