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

Different environments pose a great challenge to the outdoor robust visual perception for long-term autonomous driving and the generalization of learning-based algorithms on different environmental effects is still an open problem. Although monocular depth prediction has been well studied recently, there is few work focusing on the robust learning-based depth prediction across different environments, e.g. changing illumination and seasons, owing to the lack of such a multi-environment real-world dataset and benchmark. To this end, the first cross-season monocular depth prediction dataset and benchmark SeasonDepth is built based on CMU Visual Localization dataset. To benchmark the depth estimation performance under different environments, we investigate representative and recent state-of-the-art open-source supervised, self-supervised and domain adaptation depth prediction methods from KITTI benchmark using several newly-formulated metrics. Through extensive experimental evaluation on the proposed dataset, the influence of multiple environments on performance and robustness is analyzed qualitatively and quantitatively, showing that the long-term monocular depth prediction is still challenging even with fine-tuning. We further give promising avenues that self-supervised training and stereo geometry constraint help to enhance the robustness to changing environments. The dataset is available on https://seasondepth.github.io, and benchmark toolkit is available on https://github.com/SeasonDepth/SeasonDepth.