Skip to content

xiangjieSui/img2video

master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

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

Omnidirectional-Images-as-Moving-Camera-Videos

This is the repository of paper Omnidirectional Images as Moving Camera Videos

The database can be downloaded at here Database

Highlights:

  1. A principled computational framework for objective quality assessment of 360° images.
  2. We propose to represent an omnidirectional image by different moving camera videos.
  3. Two viewing conditions are crucial in determining the viewing behaviors of users and the perceived quality of the panorama: starting point, exploration time.

Implementation version:

  1. Matlab oiqa_metric.m (recommend)
    Requirements: Matlab>=R2017a (using higher versions, e.g., MatLab R2020a, would be better.)

  2. Pytorch im2video.py Requirements: Python>=3.6, Pytorch>=1.0

Usage:

git clone https://github.com/xiangjieSui/img2video
run demo.m/main.py

Citation

@article{sui2020omnidirectional,
  title={Omnidirectional Images as Moving Camera Videos},
  author={Xiangjie Sui and Kede Ma and Yiru Yao and Yuming Fang},
  journal = {CoRR}, 
  volume = {abs/2005.10547}, 
  year={2020}, 
  url = {https://arxiv.org/abs/2005.10547}
}

About

Omnidirectional IQA: Omnidirectional Images as Moving Camera Videos

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published