Paper

⭐ If ICELUT is helpful to your images or projects, please help star this repo. Thanks! 🤗

• Add training code and config files
• Add LUT and inference code

• python==3.7
• cuda==11.1
• numpy==1.21.5
• torch==1.8.0
• torchvision==0.9.0
• opencv-python==4.5.5.62
• matplotlib==3.5.1
• scipy==1.7.3
• GPU: NVIDIA GeForce RTX 3090
• CPU: Intel(R) Xeon(R) Platinum

• Check your cuda version

    $ls /usr/local/

• Change the cuda path in your setting

    $cd trilinear_cpp
    $vim setup.sh

    export CUDA_HOME=/usr/local/your_cuda_version && python setup.py install

• Install the package

    $sh setup.sh

• Install the package

    $cd trilinear_cpp
    $python setup.py

ATTENTION: If you follow the CPU install instruction with the GPU in your device, the default programme will still install the GPU version. If you want to only install the CPU version, please follow this step:

• Check the setup.py codes

    $vim setup.py

• Substitute the codes

    # line 5
    if torch.cuda.is_available():

    # substitute line 5 with :
    # if False

    $python inference_demo.py

Please refer to 3D LUT to prepare the FiveK datasets.

    $python train_ICELUT.py

    $python transfer2LUT.py

The retouched images generated by running inference_demo.py will be saved in the default dir: ./test_image_output

cd ./ICELUT
du -sh *.npy

% output
52K     Basis_lut.npy
204K    classifier_int8.npy
164K    Model_lsb_fp32.npy
164K    Model_msb_fp32.npy

Note that we use 10 Basis in codes rather than 20 in the paper. So the storage could be smaller (588KB v.s. 780KB).

This project is based on CLUT. Thanks for these awesome codes!