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.

© 2021 Optical Society of America

Panoramic depth estimation via supervised and unsupervised learning in indoor scenes

Keyang Zhou, Kailun Yang, and Kaiwei Wang
Appl. Opt. 60(26) 8188-8197 (2021)

Binocular stereo matching of real scenes based on a convolutional neural network and computer graphics

Liaoyu Kou, Kai Yang, Lin Luo, Yu Zhang, Jinlong Li, Yong Wang, and Liming Xie
Opt. Express 29(17) 26876-26893 (2021)

Unsupervised deep learning for depth estimation with offset pixels

Saad Imran, Sikander Bin Mukarram, Muhammad Umar Karim Khan, and Chong-Min Kyung
Opt. Express 28(6) 8619-8639 (2020)

Real-time dense-view imaging for three-dimensional light-field display based on image color calibration and self-supervised view synthesis

Xiao Guo, Xinzhu Sang, Binbin Yan, Huachun Wang, Xiaoqian Ye, Shuo Chen, Huaming Wan, Ningchi Li, Zhehao Zeng, Duo Chen, Peng Wang, and Shujun Xing
Opt. Express 30(12) 22260-22276 (2022)

Image denoising for fluorescence microscopy by supervised to self-supervised transfer learning

Yina Wang, Henry Pinkard, Emaad Khwaja, Shuqin Zhou, Laura Waller, and Bo Huang
Opt. Express 29(25) 41303-41312 (2021)