论文标题
Fisheyedistill：自我监督的单眼深度估计，fill摄影相机的顺序蒸馏
FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras
论文作者
论文摘要
在本文中，我们以一种自我监督的方式处理了鱼眼摄像机的单眼深度估计问题。自我监督深度估计的一个已知问题是，它在弱光/过度曝光条件下遭受痛苦。为了解决这个问题，我们提出了一种新型的序数蒸馏损失，从大型教师模型中提取了序数信息。这样的教师模型，由于经过大量不同数据的培训，因此可以很好地捕获深度订购信息，但缺乏保留准确的场景几何形状。结合自我监督的损失，我们表明我们的模型不仅可以在具有挑战性的环境中生成合理的深度图，而且可以更好地恢复场景几何形状。我们进一步利用AR玻璃设备的鱼眼摄像机收集室内数据集以促进评估。
In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large homogeneous regions. To tackle this issue, we propose a novel ordinal distillation loss that distills the ordinal information from a large teacher model. Such a teacher model, since having been trained on a large amount of diverse data, can capture the depth ordering information well, but lacks in preserving accurate scene geometry. Combined with self-supervised losses, we show that our model can not only generate reasonable depth maps in challenging environments but also better recover the scene geometry. We further leverage the fisheye cameras of an AR-Glasses device to collect an indoor dataset to facilitate evaluation.
