单目深度预测是近年来研究的热点，但由于缺乏真实世界的数据集和基准，在光照和季节变化等多种环境下的深度预测研究较少。在本工作中，我们从CMU视觉定位数据集通过结构和运动推导出一个新的跨季节无标度单目深度预测数据集季节性深度。然后我们制定了几个指标来衡量不同环境下的性能，使用最新的开源深度预测预训练模型来自KITTI数据集的基准。通过对所提出数据集的广泛的零射实验评估，我们表明长期的单目深度预测还远远没有解决，并提供了有前途的解决方案，在未来的工作中，包括基于几何或尺度不变训练。此外，多环境合成数据集和跨数据集验证有利于对真实环境方差的鲁棒性。

原文题目：SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments

原文：Monocular depth prediction has been well studied recently, while there are few works focused on the depth prediction across multiple environments, e.g. changing illumination and seasons, owing to the lack of such real-world dataset and benchmark. In this work, we derive a new cross-season scaleless monocular depth prediction dataset SeasonDepth from CMU Visual Localization dataset through structure from motion. And then we formulate several metrics to benchmark the performance under different environments using recent stateof-the-art open-source depth prediction pretrained models from KITTI benchmark. Through extensive zero-shot experimental evaluation on the proposed dataset, we show that the long-term monocular depth prediction is far from solved and provide promising solutions in the future work, including geometricbased or scale-invariant training. Moreover, multi-environment synthetic dataset and cross-dataset validataion are beneficial to the robustness to real-world environmental variance.

原文作者：Hanjiang Hu, Baoquan Yang, Weiang Shi, Zhijian Qiao, Hesheng Wang

原文地址：https://arxiv.org/abs/2011.04408