We propose DeepV2D, an end-to-end deep learning architecture for predicting depth from video. DeepV2D combines the representation ability of neural networks with the geometric principles governing image formation. We compose a collection of classical geometric algorithms, which are converted into trainable modules and combined into an end-to-end differentiable architecture. DeepV2D interleaves two stages: motion estimation and depth estimation. During inference, motion and depth estimation are alternated and converge to accurate depth. Code is available https://github.com/princeton-vl/DeepV2D.
@article{arxiv.1812.04605,
title = {DeepV2D: Video to Depth with Differentiable Structure from Motion},
author = {Zachary Teed and Jia Deng},
journal= {arXiv preprint arXiv:1812.04605},
year = {2020}
}