paper-with-me

홈 › Papers

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

2021-08-08 · ICCV 2021 10 · Songhua Liu, Tianwei Lin, Dongliang He, Fu Li, Meiling Wang, Xin Li, Zhengxing Sun, Qian Li, Errui Ding

Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Existing solutions either attentively fuse deep style feature into deep content feature without considering feature distributions, or adaptively normalize deep content feature according to the style such that their global statistics are matched. Although effective, leaving shallow feature unexplored and without locally considering feature statistics, they are prone to unnatural output with unpleasing local distortions. To alleviate this problem, in this paper, we propose a novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis. Specifically, spatial attention score is learnt from both shallow and deep features of content and style images. Then per-point weighted statistics are calculated by regarding a style feature point as a distribution of attention-weighted output of all style feature points. Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics. Besides, a novel local feature loss is derived based on AdaAttN to enhance local visual quality. We also extend AdaAttN to be ready for video style transfer with slight modifications. Experiments demonstrate that our method achieves state-of-the-art arbitrary image/video style transfer. Codes and models are available.

📄 PDF Abstract BibTeX arXiv:2108.03647

Code (3)

huage001/adaattn 공식 구현 pytorch
wzmsltw/adaattn 공식 구현 paddle
gaetano-signorelli/Attention-Style-Transfer tf

Tasks

Style TransferVideo Style Transfer

Methods 이 논문이 사용한 방법론

Attentive Normalization 설명 없음

Similar Papers 제목 키워드 기반

All-to-key Attention for Arbitrary Style Transfer

2022-12-08 · ICCV 2023 1 · Mingrui Zhu, Xiao He, Nannan Wang, Xiaoyu Wang 외

Attention-based arbitrary style transfer studies have shown promising performance in synthesizing vivid local style details. They typically use the all-to-all attention mechanism -- each position of content features is f…

AllPositionStyle Transfer

HSI: A Holistic Style Injector for Arbitrary Style Transfer

2025-02-05 · CVPR 2025 1 · Shuhao Zhang, Hui Kang, Yang Liu, Fang Mei 외

Attention-based arbitrary style transfer methods have gained significant attention recently due to their impressive ability to synthesize style details. However, the point-wise matching within the attention mechanism may…

Semantic SimilaritySemantic Textual SimilarityStyle Transfer

Arbitrary Style Transfer with Style-Attentional Networks

2018-12-06 · CVPR 2019 6 · Dae Young Park, Kwang Hee Lee

Arbitrary style transfer aims to synthesize a content image with the style of an image to create a third image that has never been seen before. Recent arbitrary style transfer algorithms find it challenging to balance th…

DecoderStyle Transfer

Neural arbitrary style transfer for portrait images using the attention mechanism

2020-02-17 · S. A. Berezin, V. M. Volkova

Arbitrary style transfer is the task of synthesis of an image that has never been seen before, using two given images: content image and style image. The content image forms the structure, the basic geometric lines and s…

Style Transfer

Playing Lottery Tickets in Style Transfer Models

2022-03-25 · Meihao Kong, Jing Huo, Wenbin Li, Jing Wu 외

Style transfer has achieved great success and attracted a wide range of attention from both academic and industrial communities due to its flexible application scenarios. However, the dependence on a pretty large VGG-bas…

Style Transfer