We present a self-supervised learning framework to estimate the individual
object motion and monocular depth from video. We model the object motion as a 6
degree-of-freedom rigid-body transformation. The instance segmentation mask is
leveraged to introduce the information of object. Compared with methods which
predict dense optical flow map to model the motion, our approach significantly
reduces the number of values to be estimated. Our system eliminates the scale
ambiguity of motion prediction through imposing a novel geometric constraint
loss term. Experiments on KITTI driving dataset demonstrate our system is
capable to capture the object motion without external annotation. Our system
outperforms previous self-supervised approaches in terms of 3D scene flow
prediction, and contribute to the disparity prediction in dynamic area.

本文提出了一种自监督学习框架，从视频中估算单个对象的运动和单眼深度，并将对象运动建模为六个自由度刚体变换；此外，该方法还使用实例分割掩码引入对象信息，并通过引入新的几何约束损失项消除运动预测的尺度歧义，实验结果表明，该框架在不需要外部注释的情况下处理数据并能够捕捉对象的运动，与自监督研究方法相比，在 3D 场景流预测方面有更好的表现，对动态区域的视差预测也有所贡献。