DeepV2D: Video to Depth with Differentiable Structure from Motion

December 11, 2018 · Entered Twilight · 🏛 International Conference on Learning Representations

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, cfgs, data, deepv2d, demos, evaluation, readme.md, training

Authors Zachary Teed, Jia Deng arXiv ID 1812.04605 Category cs.CV: Computer Vision Citations 298 Venue International Conference on Learning Representations Repository https://github.com/princeton-vl/DeepV2D ⭐ 671 Last Checked 1 month ago

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. Code is available https://github.com/princeton-vl/DeepV2D.