Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video

Understand

Estimating geometric elements such as depth, camera motion, and optical flow from images is an important part of the robot's visual perception.

• We use a joint self-supervised method to estimate the three geometric elements.
• Depth network, optical flow network and camera motion network are independent of each other but are jointly optimized during training phase.
• Compared with independent training, joint training can make full use of the geometric relationship between geometric elements and provide dynamic and static information of the scene.