构建首个跨高度3D重建基准数据集，助力应急响应与执法
Unconstrained Large-scale 3D Reconstruction and Rendering across Altitudes
- 融合地面、安防、空中多视角相机数据，应对真实场景挑战
- 首次独立评估未标定相机校准与新视角渲染质量
- 为灾难救援和执法提供可导航的高保真3D模型解决方案
生成逼真的可导航3D场景模型需要大量精心采集的图像，但这类数据常难以获取，尤其在灾害救援或执法场景中。现实挑战包括图像数量有限、相机姿态不一致、光照差异大以及不同高度拍摄导致的视角极端差异。为此，我们构建了首个基于多校准地面、安防及空中相机的3D重建与新视角合成公开基准数据集。该数据集涵盖真实世界难题，独立评估未标定相机的校准性能与新视图渲染质量，展示了当前主流方法的基线表现，并指出了未来研究的关键挑战。
原文摘要 · Abstract (English)
Production of photorealistic, navigable 3D site models requires a large volume of carefully collected images that are often unavailable to first responders for disaster relief or law enforcement. Real-world challenges include limited numbers of images, heterogeneous unposed cameras, inconsistent lighting, and extreme viewpoint differences for images collected from varying altitudes. To promote research aimed at addressing these challenges, we have developed the first public benchmark dataset for 3D reconstruction and novel view synthesis based on multiple calibrated ground-level, security-level, and airborne cameras. We present datasets that pose real-world challenges, independently evaluate calibration of unposed cameras and quality of novel rendered views, demonstrate baseline performance using recent state-of-practice methods, and identify challenges for further research.
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。