CNNs for Style Transfer of Digital to Film Photography
This work addresses a niche problem for photography enthusiasts by incrementally exploring loss functions and training techniques for style transfer, with limited practical impact.
The authors tackled the problem of transferring the stylistic effects of Cinestill800T film to digital photography using convolutional neural networks, finding that a combination of MSE and VGG loss functions produced the best color results but failed to generate high-quality grain or halation.
The use of deep learning in stylistic effect generation has seen increasing use over recent years. In this work, we use simple convolutional neural networks to model Cinestill800T film given a digital input. We test the effect of different loss functions, the addition of an input noise channel and the use of random scales of patches during training. We find that a combination of MSE/VGG loss gives the best colour production and that some grain can be produced, but it is not of a high quality, and no halation is produced. We contribute our dataset of aligned paired images taken with a film and digital camera for further work.