DeepV2D: Video to Depth with Differentiable Structure from Motion

Zachary Teed; Jia Deng

ICLR 2020poster305 citations

DeepV2D: Video to Depth with Differentiable Structure from Motion

Abstract

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.

Structure-from-MotionVideo to DepthDense Depth Estimation

BibTeX

@inproceedings{
Teed2020DeepV2D:,
title={DeepV2D: Video to Depth with Differentiable Structure from Motion},
author={Zachary Teed and Jia Deng},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=HJeO7RNKPr}
}