스타일 전이 기술의 사용성 향상을 위한 attention map 기반 모델 최적화 = Optimization of attention map based model for improving the usability of style transfer techniques

다국어 초록 (Multilingual Abstract)

Style transfer is one of deep learning-based image processing techniques that has been actively researched recently. These research efforts have led to significant improvements in the quality of result images. Style transfer is a technology that takes a content image and a style image as inputs and generates a transformed result image by applying the characteristics of the style image to the content image. It is becoming increasingly important in exploiting the diversity of digital content. To improve the usability of style transfer technology, ensuring stable performance is crucial. Recently, in the field of natural language processing, the concept of Transformers has been actively utilized. Attention maps, which forms the basis of Transformers, is also being actively applied and researched in the development of style transfer techniques. In this paper, we analyze the representative techniques SANet and AdaAttN and propose a novel attention map-based structure which can generate improved style transfer results. The results demonstrate that the proposed technique effectively preserves the structure of the content image while applying the characteristics of the style image.

참고문헌 (Reference)

1 Fred Phillips, "Wiki Art Gallery, Inc.: A Case for Critical Thinking" American Accounting Association 26 (26): 593-608, 2011

2 K. Simonyan, "Very deep convolutional networks for large-scale image recognition" 2015

3 Y. Li, "Universal style transfer via feature.transforms" 386-396, 2017

4 D. Ulyanov, "Texture networks : Feed-forward synthesis of textures and stylized images" 1349-1357, 2016

5 X. Wu, "Styleformer : Real-time arbitrary style transfer via parametric style composition" 14618-14627, 2021

6 Yingying Deng, "StyTr2 :Image Style Transfer with Transformers" 2022

7 T. Lin, "Microsoft coco: Common objects in context" 740-, 2014

8 L. A. Gatys, "Image style transfer using convolutional neural networks" 2414-2423, 2016

9 L. Sheng, "Avatar-net: Multi-scale zero-shot style transfer by feature decoration" 8242-8250, 2018

10 Y. Yao, "Attention-aware multi-stroke style transfer" 1467-1475, 2019

11 A. Vaswani, "Attention is all you need" 5998-6008, 2017

12 D. Y. Park, "Arbitrary style transfer with style-attentional networks" 5880-5888, 2019

13 Y. Deng, "Arbitrary style transfer via multi-adaptation network" 2719-2727, 2020

14 X. Huang, "Arbitrary style transfer in real-time with adaptive instance normalization" 1501-1510, 2017

15 S. Liu, "AdaAttn: Revisit attention mechanism in arbitrary neural style transfer" 2021