/DPE-MEF

This is the code for "Multi-Exposure Image Fusion via Deep Perceptual Enhancement".

Primary LanguagePython

DPE-MEF

This is the PyTorch implementation of paper "Multi-exposure image fusion via deep perceptual enhancement".

Architecture

DPE-MEF pipeline

Fusion Results

fusion result

Dependencies

The released version of DPE-MEF was implemented and tested on Ubuntu 16.04 with:

  • Python = 3.6.12
  • PyTorch = 1.2.0
  • torchvision = 0.4.0
  • opencv-python = 4.4.0.46
  • NVIDIA GPU + CUDA 10.0

Train

Reorganizing, release soon.

Test

Run the following command:

python test_ALL.py

The fused results can be found in ./results.