CNNs for Style Transfer of Digital to Film Photography
Pierre Mackenzie, Mika Senghaas, Raphael Achddou

TL;DR
This paper explores using convolutional neural networks to convert digital images into film-like photographs, testing various training techniques and loss functions, and providing a new dataset for future research.
Contribution
It introduces a CNN-based approach for digital-to-film style transfer and shares a dataset of paired images to facilitate further studies.
Findings
MSE/VGG loss yields best color reproduction
Some film grain can be simulated, but quality is limited
No halation effect was produced in the results
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Advanced Data Compression Techniques · Generative Adversarial Networks and Image Synthesis
