/LIE-IQA-mindspore

The MindSpore Implementantion of Quality Assessment for Enhanced Low-light Image

LIE-IQA

The MindSpore implementation of LIE-IQA is released HERE and is merged with MindSpore/contrib on Gitee.

You can get the Pytorch implementation here LIE-IQA-pytorch. It is worth noting that the MindSpore implementation of Image Intrinsic Decomposition (IID) Module is different from the Pytorch implementation , but there is not much difference in performance. Please refer to the specific code for details.

The code on Pytorchwill be released soon.

Requirements

  • Python 3.7.5
  • MindSpore 1.2.1
  • CUDA 10.1

Quality Assessment for Enhanced Low-light Image

  • LIE-IQA Framework

  • Performance on LIE-IQA Dataset

  • Performance on General Scene IQA Dataset

    • LIVE, MDID, CSIQ

Quality Optimization for Low-light Image Enhancement

  • Optimization framework