Skip to content

Latest commit

 

History

History
22 lines (20 loc) · 605 Bytes

README.md

File metadata and controls

22 lines (20 loc) · 605 Bytes

Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes

testing code for the paper Wang etal. 3DV19

Installation

tested with Python 3.6 with cuda 9.0 on Ubuntu16.04

install dependicies:

  • opencv-python
  • numpy
  • pytorch 0.4.1

install flownet2.0

cd networks/flownet2
bash install.sh

download model

  • download ckpts.tar
  • extract the content to ./ckpts/

predict depth from 2 images

CUDA_VISIBLE_DEVICES=0 python demo.py demo/im1.jpg demo/im2.jpg