构建365段高精度摄像机位姿视频数据集，支持多样场景与新评估标准。
Princeton365: A Diverse Dataset with Accurate Camera Pose
- 用校准板和360°摄像头系统采集真实位姿，确保精度与多样性。
- 提出基于光流的尺度感知评估指标，可跨场景对比SLAM性能。
- 新增非朗伯反射与360°轨迹的新型视角合成挑战任务。
我们提出Princeton365，一个包含365段视频的大规模多样化数据集，具有精确的摄像机位姿。该数据集通过一种新颖的真值采集框架，结合校准板与360°摄像头，弥合了当前SLAM基准中精度与数据多样性之间的差距。数据涵盖室内、室外及物体扫描视频，提供同步的单目与双目RGB视频以及IMU数据。我们还提出一种新的、基于光流的场景尺度感知评价指标，用于评估SLAM性能。相比现有平均轨迹误差（ATE）等指标，该指标可实现跨场景比较，帮助研究者分析算法失效模式。此外，我们构建了一个更具挑战性的新视角合成（NVS）基准，覆盖现有基准未涵盖的情况，如完全非朗伯反射场景及360°相机轨迹。更多内容请访问https://princeton365.cs.princeton.edu获取数据、代码、视频及提交方式。
原文摘要 · Abstract (English)
We introduce Princeton365, a large-scale diverse dataset of 365 videos with accurate camera pose. Our dataset bridges the gap between accuracy and data diversity in current SLAM benchmarks by introducing a novel ground truth collection framework that leverages calibration boards and a 360-camera. We collect indoor, outdoor, and object scanning videos with synchronized monocular and stereo RGB video outputs as well as IMU. We further propose a new scene scale-aware evaluation metric for SLAM based on the optical flow induced by the camera pose estimation error. In contrast to the current metrics, our new metric allows for comparison between the performance of SLAM methods across scenes as opposed to existing metrics such as Average Trajectory Error (ATE), allowing researchers to analyze the failure modes of their methods. We also propose a challenging Novel View Synthesis benchmark that covers cases not covered by current NVS benchmarks, such as fully non-Lambertian scenes with 360-degree camera trajectories. Please visit https://princeton365.cs.princeton.edu for the dataset, code, videos, and submission.
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。