May 25, 2021 · We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference ...

Jun 18, 2021 · This paper proposes a video-based unsupervised depth learning method. Thanks to the proposed geometry consistency loss and masking scheme, our ...

This codebase was developed and tested with python 3.6, Pytorch 1.0.1, and CUDA 10.0 on Ubuntu 16.04. It is based on Clement Pinard's SfMLearner implementation.

This is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a ...

With iterative sampling and training from videos, depth predictions on each consecutive image pair would be scale-consistent, and the frame-to-frame ...

We propose a monocular depth estimation method SC-Depth , which requires only unlabelled videos for training and enables the scale-consistent prediction at ...

We propose a monocular depth estimation method SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at ...

A monocular depth estimation method SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference ...

May 2, 2020 · This paper "Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video (NIPS 2019)" can also achieve 'consistent depth ...

Aug 28, 2019 · This is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a ...