adaattn's Introduction

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

[Paper] [Paddle Implementation]

Overview

This repository contains the official PaddlePaddle implementation of paper:

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer,

Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, Errui Ding

ICCV 2021

Prerequisites

Linux or macOS
Python 3
PaddlePaddle 2.0+ and other dependencies (visdom, dominate, and other common python libs)

Getting Started

Clone this repository:

git clone https://github.com/wzmsltw/AdaAttN
cd AdaAttN

Citation

If you find ideas or codes useful for your research, please cite:

@inproceedings{liu2021adaattn,
  title={AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer},
  author={Liu, Songhua and Lin, Tianwei and He, Dongliang and Li, Fu and Wang, Meiling and Li, Xin and Sun, Zhengxing and Li, Qian and Ding, Errui},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  year={2021}
}

Contact

For any question, please file an issue or contact

Songhua Liu: [email protected]
Tianwei Lin: [email protected]

adaattn's People

Contributors

Stargazers

Watchers

adaattn's Issues

code for AdaAttN: Revisit_Attention_Mechanism_in_Arbitrary_Neural_Style_Transfer

Hi,
I read your paper and it looks very interesting.
Can you please share your code + pretrained model?
It is not available under "PaddlePaddle" git.
Thanks in advanced.
Ofer

[paper] About the cos in paper

Hi , About the formula 12 in the paper
Si,j is the cosine similarity results, which use the + 1
and the formula 12 in the paper
Di,j also s the cosine similarity results, which use 1 -
can you explain for a little? Thanks!