This example PerceptiLabs model, shows how a special type of convolutional neural network (CNN) called a U-Net, can be used to enhance dark photos.
Note: This model is not compatible with PerceptiLabs 0.12 as the UI and components have changed.
The concept behind this approach is based on that described in Learning to See in the Dark (SID), a scholarly article published on https://arxiv.org/abs/1805.01934 that demonstrates how machine learning (ML) can be used in place of traditional digital image processing techniques, to enhance very dark images.
The resources provided in this GitHub repo, supplement our Using a U-Net to Enhance Dark Photos documentation topic.
Happy hacking!
This repo has the following structure:
- /Data: contains pre-processed versions of the raw data/reference image pairs to use for training that originated as raw camera data files in the SID project. The pairs of images are stored in the following subdirectories. Note that each pair uses the same filenames for the raw data and reference images:
- /Data/short_cropped: contains the raw, dark camera sensor data images that have been preprocessed, cropped, and spatially reduced to a resolution of 512x512x4 in .tiff format.
- /Data/long_cropped: contains the corresponding reference images with the ideal lighting that have been preprocessed and cropped to a resolution of 1024x1024x3 (sRGB) in .tiff format.
- /SID_Model: contains the PerceptiLabs model file (model.json) for use in PerceptiLabs v0.11.
Note: you must be running PerceptiLabs 0.10.0 or 0.11 to load this model. This model is not compatible with PerceptiLabs 0.12.
Follow the steps below to load the sample model in PerceptiLabs:
- Clone or download the sample model from GitHub.
- On the ModelHub screen, import the sample model into PerceptiLabs. Note that this model is not compatible with PerceptiLabs 0.12 as the UI and components have changed. When prompted for the model's folder, navigate to and select the location of the model.json file.
- Open the topmost Data component in the model workspace and set its folder to the long_cropped directory. Open the second Data component in the model workspace and set its folder to the short_cropped directory.
Got questions, feedback, or want to join a community of machine learning practitioners working with exciting tools and projects? Check out our Community page!