Self-supervised stereo depth estimation based on bi-directional pixel-movement learning.

ABSTRACT

Stereo depth estimation is an efficient method to perceive three-dimensional structures in real scenes. In this paper, we propose a novel self-supervised method, to the best of our knowledge, to extract depth information by learning bi-directional pixel movement with convolutional neural networks (CNNs). Given left and right views, we use CNNs to learn the task of middle-view synthesis for perceiving bi-directional pixel movement from left-right views to the middle view. The information of pixel movement will be stored in the features after CNNs are trained. Then we use several convolutional layers to extract the information of pixel movement for estimating a depth map of the given scene. Experiments show that our proposed method can significantly provide a high-quality depth map using only a color image as a supervisory signal.