We propose a monocular depth estimator SC-Depth, which requires only
unlabelled videos for training and enables the scale-consistent prediction at
inference time. Our contributions include: (i) we propose a geometry
consistency loss, which penalizes the inconsistency of predicted depths between
adjacent views; (ii) we propose a self-discovered mask to automatically
localize moving objects that violate the underlying static scene assumption and
cause noisy signals during training; (iii) we demonstrate the efficacy of each
component with a detailed ablation study and show high-quality depth estimation
results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of
scale-consistent prediction, we show that our monocular-trained deep networks
are readily integrated into the ORB-SLAM2 system for more robust and accurate
tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in
KITTI, and it generalizes well to the KAIST dataset without additional
training. Finally, we provide several demos for qualitative evaluation.

本文提出了一种单目深度估计器 SC-Depth，它只需要使用未标记的视频进行训练，并能在推理时实现尺度一致的预测。我们的贡献包括：(i) 我们提出了一种几何一致性损失，惩罚相邻视角之间预测深度的不一致性；(ii) 我们提出了自动定位违反基本静态场景假设并在训练过程中引起噪声信号的移动对象的自我发现掩码；(iii) 我们通过详细的消融研究证明了每个组件的功效，并展示了在 KITTI 和 NYUv2 数据集中高质量的深度估计结果。此外，由于具有尺度一致性预测的能力，我们展示了我们训练的单目深层网络可以轻松地集成到 ORB-SLAM2 系统中以实现更强大和准确的跟踪。提出的混合 Pseudo-RGBD SLAM 在 KITTI 中具有很强的性能，并且在没有额外训练的情况下很好地推广到 KAIST 数据集。最后，我们提供了几个演示以进行定性评估。

从视频中无监督学习尺度一致的深度

Unsupervised Scale-consistent Depth Learning from Video

Recent work has shown that CNN-based depth and ego-motion estimators can be
learned using unlabelled monocular videos. However, the performance is limited
by unidentified moving objects that violate the underlying static scene
assumption in geometric image reconstruction. More significantly, due to lack
of proper constraints, networks output scale-inconsistent results over
different samples, i.e., the ego-motion network cannot provide full camera
trajectories over a long video sequence because of the per-frame scale
ambiguity. This paper tackles these challenges by proposing a geometry
consistency loss for scale-consistent predictions and an induced
self-discovered mask for handling moving objects and occlusions. Since we do
not leverage multi-task learning like recent works, our framework is much
simpler and more efficient. Comprehensive evaluation results demonstrate that
our depth estimator achieves the state-of-the-art performance on the KITTI
dataset. Moreover, we show that our ego-motion network is able to predict a
globally scale-consistent camera trajectory for long video sequences, and the
resulting visual odometry accuracy is competitive with the recent model that is
trained using stereo videos. To the best of our knowledge, this is the first
work to show that deep networks trained using unlabelled monocular videos can
predict globally scale-consistent camera trajectories over a long video
sequence.

本文介绍了一种基于几何一致性损失和自发现遮罩的深度估计和自我运动估计模型，模型能够处理运动物体和目标的遮挡问题并保证不同样本间的比例一致性。从实验结果来看，我们提出的深度估计模型在 KITTI 数据集上性能最好，并且我们提出的自动驾驶路线规划模型相对于之前的模型在预测全局一致的相机轨迹上有着很大的优势。