Skip to content

Latest commit

 

History

History
31 lines (23 loc) · 932 Bytes

README.md

File metadata and controls

31 lines (23 loc) · 932 Bytes
Raw

Python 3.7

LFSR-AFR

Keunsoo Ko, Yeong Jun Koh, SoonKeun Chang, and Chang-Su Kim

Official PyTorch Code for "Light Field Super-Resolution via Adaptive Feature Remixing, IEEE Trans. Image Process., vol. 30, pp. 4114-4128, Apr. 2021"

Requirements

  • PyTorch 1.3.1 (Other versions can cause different results)
  • python 3.7

Installation

Download repository:

    $ git clone https://github.com/keunsoo-ko/LFSR-AFR.git

Download pre-trained model parameters

Usage

Run Test for the spatial super resolution on the HCI dataset with the factor x2:

    $ python demo.py --mode SR --path LFSR-AFR.pth(put downloaded model path)

Run Test for the angular super resolution on the HCI dataset with the factor x2:

    $ python demo.py --mode AR --path LFSR-AFR.pth