Helvipad：用于全方位立体深度估计的真实世界数据集
Helvipad: A Real-World Dataset for Omnidirectional Stereo Depth Estimation
AI总结：
针对全方位立体深度估计数据匮乏问题，构建含4万帧真实世界视频的Helvipad数据集，通过相机与LiDAR提供深度标签，并改进立体模型以提升全方位深度估计精度。
摘要：
尽管立体深度估计取得了进展，但全方位成像仍未被充分探索，这主要是由于缺乏合适的数据。我们推出了Helvipad，一个用于全方位立体深度估计的真实世界数据集，包含来自不同环境视频序列的4万帧视频帧，包括各种光照条件下拥挤的室内和室外场景。该数据集使用两台360°相机以上下配置和一台LiDAR传感器采集，通过将3D点云投影到等距柱状图像上，提供了准确的深度和视差标签。此外，我们通过使用深度补全，提供了一个标签密度增加的增强训练集。我们对标准和全方位图像的前沿立体深度估计模型进行了基准测试。结果表明，尽管最近的立体方法表现尚可，但在全方位成像中准确估计深度仍存在挑战。为解决这一问题，我们对立体模型进行了必要的调整，从而提高了性能。
英文摘要：
Despite progress in stereo depth estimation, omnidirectional imaging remains underexplored, mainly due to the lack of appropriate data. We introduce Helvipad, a real-world dataset for omnidirectional stereo depth estimation, featuring 40K video frames from video sequences across diverse environments, including crowded indoor and outdoor scenes with various lighting conditions. Collected using two 360° cameras in a top-bottom setup and a LiDAR sensor, the dataset includes accurate depth and disparity labels by projecting 3D point clouds onto equirectangular images. Additionally, we provide an augmented training set with an increased label density by using depth completion. We benchmark leading stereo depth estimation models for both standard and omnidirectional images. The results show that while recent stereo methods perform decently, a challenge persists in accurately estimating depth in omnidirectional imaging. To address this, we introduce necessary adaptations to stereo models, leading to improved performance.
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。
