Skip to content

voyleg/perceptual-depth-sr

master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
src
 
 
 
 
 
 
 
 

Perceptual Depth Super-Resolution

This is the official repository for the paper Perceptual Deep Depth Super-Resolution. It contains trained MSG-V models for x4 and x8 super-resolution and IPython notebook with a usage example. It also contains the implementation of MSEv loss function and usage example.

[paper] [supp] [project page]

Installation

To run the code you will need python3.7 and the packages from environment.yml. All of them can be installed via conda with

conda env create -f environment.yml

Alternatively, you can build an Nvdia-Docker image with all required dependencies using the provided Dockerfile:

git clone https://github.com/voyleg/perceptual-depth-sr
cd perceptual-depth-sr
docker build -t perceptual-depth-sr .

and run Jupyter in the container

nvidia-docker run --rm -it -p 8888:8888 --mount type=bind,source=$(pwd),target=/code perceptual-depth-sr bash -c 'cd /code && jupyter notebook --ip="*" --no-browser --allow-root'

Citation

@inproceedings{voynov2019perceptual,
  title={Perceptual deep depth super-resolution},
  author={Voynov, Oleg and Artemov, Alexey and Egiazarian, Vage and Notchenko, Alexander and Bobrovskikh, Gleb and Burnaev, Evgeny and Zorin, Denis},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={5653--5663},
  year={2019}
}

About

Perceptual Deep Depth Super-Resolution, ICCV 2019

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published