# Meta Networks for Neural Style Transfer

arXiv: https://arxiv.org/abs/1709.04111 · HTML: https://mlsanity.com/paper/1709.04111/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2017.

## Built on by (most cited first, 5 of 5)

- [Principled Weight Initialization for Hypernetworks](https://mlsanity.com/paper/2312.08399/) (2023)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworks](https://mlsanity.com/paper/2101.02194/) (2021)
- [Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer](https://mlsanity.com/paper/2304.11818/) (2023)
- [Computing Multiple Image Reconstructions with a Single Hypernetwork](https://mlsanity.com/paper/2202.11009/) (2022)

## Abstract (arXiv)

In this paper we propose a new method to get the specified network parameters through one time feed-forward propagation of the meta networks and explore the application to neural style transfer. Recent works on style transfer typically need to train image transformation networks for every new style, and the style is encoded in the network parameters by enormous iterations of stochastic gradient descent. To tackle these issues, we build a meta network which takes in the style image and produces a corresponding image transformations network directly. Compared with optimization-based methods for every style, our meta networks can handle an arbitrary new style within 19ms seconds on one modern GPU card. The fast image transformation network generated by our meta network is only 449KB, which is capable of real-time executing on a mobile device. We also investigate the manifold of the style transfer networks by operating the hidden features from meta networks. Experiments have well validated the effectiveness of our method. Code and trained models has been released https://github.com/FalongShen/styletransfer.