Title: Consistent Video Depth Estimation Using Python And Machine Learning
About This Machine Learning Project:
In this project, Xuan Luo, Jia-Bin Huang, Richard Szeliski, Kevin Matzen and Johannes Kopf present an algorithm for reconstructing dense, geometrically consistent depth for all pixels in a monocular video.
They leverage a conventional structure-from-motion reconstruction to establish geometric constraints on pixels in the video. Unlike the ad-hoc priors in classical reconstruction, they use a learning-based prior, i.e., a convolutional neural network trained for single-image depth estimation.
Code: Consistent Video Depth Estimation
Related Projects: