Skip to content

PyTorch implementation of Deep Ordinal Regression Network for Monocular Depth Estimation

Notifications You must be signed in to change notification settings

dontLoveBugs/DORN_pytorch

Repository files navigation

DORN implemented in Pytorch 0.4.1

Introduction

This is a PyTorch(0.4.1) implementation of Deep Ordinal Regression Network for Monocular Depth Estimation. At present, we can provide train script in NYU Depth V2 dataset. KITTI will be available soon!

Note: we modify the ordinal layer using matrix operation, making trianing faster.

TODO

  • DORN model in nyu and kitti
  • Training DORN on nyu and kitti datasets
  • Results evaluation on nyu test set
  • Calculate alpha and beta in nyu dataset
  • Realize the ordinal loss in paper

About

PyTorch implementation of Deep Ordinal Regression Network for Monocular Depth Estimation

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages