The lf-internet's intro from cv-ip

lf-internet's Introduction

PyTorch implementation of "Spatial-Angular Interaction for Light Field Image Super-Resolution", ECCV 2020.

Note: We have revised the paper and compared LF-InterNet to LF-ATO (CVPR2020). See details in the current version. [arXiv]

Overview

Fig. 1: An overview of our LF-InterNet.

Fig. 2: An illustration of angular feature extractor (AFE) and spatial feature extractor (SFE).

Requirement

PyTorch 1.3.0, torchvision 0.4.1. The code is tested with python=3.7, cuda=9.0.
Matlab (For training/test data generation and performance evaluation)

Train

Training codes will be released soon.

Test

Download the test sets and unzip them to ./data. Here, we provide a demo test set (data_demo.zip) which only includes one test scene, and we also provide the full test set (data.zip) which is used in our paper.
Download our pretrained models (log.zip) and unzip them to ./log.
Run GenerateDataForTest.m to generate test data.
Run test.py to perform a demo inference. Note that, the selected pretrained model should match the generated input data and the preset network architecture. Initial results (.mat files) will be saved to ./results.
Run evaluation.m to calculate PSNR and SSIM scores and transform initial results (.mat files) into .png images.

Quantitative Results

Qualitative Results

Efficiency

Performance w.r.t. Perspectives

Performance Under Real-World Degradation

Citiation

If you find this work helpful, please consider citing the following paper:

@article{LF-InterNet,
  title={Spatial-Angular Interaction for Light Field Image Super-Resolution},
  author={Wang, Yingqian and Wang, Longguang and Yang, Jungang and An, Wei and Yu, Jingyi and Guo, Yulan},
  journal={arXiv preprint arXiv:1912.07849},
  year={2019}
}