/exposure

Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.

Primary LanguagePythonMIT LicenseMIT

Exposure:
A White-Box Photo Post-Processing Framework

[Paper] [PDF Slides]

Installation

Requirements: python3 and tensorflow. Tested on Ubuntu 16.04 and Arch Linux. OS X may also work, though not tested.

sudo pip3 install tensorflow-gpu opencv-python tifffile scikit-image
git clone https://github.com/yuanming-hu/exposure --recursive
cd exposure

Using the pretrained model

  • python3 evaluate.py example pretrained models/sample_inputs/*.tif
  • Results will be generated at outputs/

Training your own model on the FiveK dataset

  • python3 fetch_fivek.py
    • This script will automatically setup the MIT-Adobe FiveK Dataset
    • Total download size: ~2.4GB
    • Only the downsampled and data-augmented image pack will be downloaded. Original dataset is large as 50GB and needs Adobe Lightroom to pre-process the RAW files. If you want to do data pre-processing and augmentation on your own, please follow the instructions here.
  • python3 train.py example test
    • This command will load config_example.py,
    • and create a model folder at models/example/test
  • Have a cup of tea and wait for the model to be trained (~100 min on a GTX 1080 Ti)
    • The training progress is visualized at folder models/example/test/images-example-test/*.png
    • Legend: top row: learned operating sequences; bottom row: replay buffer, result output samples, target output samples
  • python3 evaluate.py example test models/sample_inputs/*.tif (This will load models/example/test)
  • Results will be generated at outputs/

Training on your own dataset

Please check out https://github.com/Abhishek-Gawande/exposure/blob/master/config_sintel.py

Visual Results

Related Research Projects and Implementations