Exploring the structure of a real-time, arbitrary neural artistic stylization network
Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin, Jonathon Shlens
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/magenta/magenta/blob/master/magenta/models/arbitrary_image_stylization/README.mdOfficialtf★ 0
- github.com/RemiArbache/style-transfer-M2tf★ 1
- github.com/sha256burim/Implementation-of-TensorFlow-Fast-GAN-Neural-Style-Transfertf★ 0
- github.com/yangyucheng000/arbitrary_image_stylizationmindspore★ 0
- github.com/AlexAdamov/StylizedPictf★ 0
- github.com/Mind23-2/MindCode-8mindspore★ 0
- github.com/mindspore-ai/models/tree/master/research/cv/ArbitraryStyleTransfermindspore★ 0
- github.com/xiuyu0000/papers_with_examples/tree/main/arbitrary_image_stylizationmindspore★ 0
- github.com/code-implementation1/Code2/tree/main/ArbitraryStyleTransfermindspore★ 0
- github.com/billsun9/automated-style-transfertf★ 0
Abstract
In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content/style image pair. We build upon recent work leveraging conditional instance normalization for multi-style transfer networks by learning to predict the conditional instance normalization parameters directly from a style image. The model is successfully trained on a corpus of roughly 80,000 paintings and is able to generalize to paintings previously unobserved. We demonstrate that the learned embedding space is smooth and contains a rich structure and organizes semantic information associated with paintings in an entirely unsupervised manner.