Deep Image Style Transfer from Freeform Text
Tejas Santanam, Mengyang Liu, Jiangyue Yu, Zhaodong Yang

TL;DR
This paper introduces a novel deep neural style transfer method that generates style images from freeform text descriptions, enabling more flexible and high-quality image stylization.
Contribution
It presents a seamless pipeline combining language and style transfer models to create style images from text, improving style transfer quality over baseline methods.
Findings
Generated style images closely match text descriptions
Output images have similar losses and better quality
The method demonstrates effective integration of language and style transfer models
Abstract
This paper creates a novel method of deep neural style transfer by generating style images from freeform user text input. The language model and style transfer model form a seamless pipeline that can create output images with similar losses and improved quality when compared to baseline style transfer methods. The language model returns a closely matching image given a style text and description input, which is then passed to the style transfer model with an input content image to create a final output. A proof-of-concept tool is also developed to integrate the models and demonstrate the effectiveness of deep image style transfer from freeform text.
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.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Face recognition and analysis · Human Motion and Animation
