얼굴 속성 편집을 위한 마스크 정보를 활용한 개선된 STGAN
Improved STGAN for Facial Attribute Editing by Utilizing Mask Information
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 머리카락과 모자 영역의 마스크 정보를 활용하여 더 자연스러운 얼굴 속성 편집(facial attribute editing)을 수행하는 모델을 제안한다. 최신 얼굴 속성 편집 연구인 STGAN은 다중얼굴 속성을 자연스럽게 편집하는 성과를 보였다. 그러나 머리카락과 관련된 속성을 편집할 때부자연스러운 결과를 생성할 수 있다. 제안하는 방법의 핵심 아이디어는 기존 모델에서 부족했던얼굴 영역의 정보를 모델에 추가로 반영하는 것이다. 이를 위해 세 가지 아이디어를 적용한다. 첫째로 마스크를 통해 머리카락 면적 속성을 추가하여 머리카락 정보를 보완한다. 둘째로 순환 일관성 손실(cycle consistency loss)을 추가하여 영상의 불필요한 변화를 억제한다. 셋째로 모자 분할신경망을 추가하여 모자 영역 왜곡을 방지한다. 정성적 평가를 통해 제안하는 방법 적용 여부에따른 유효성을 평가 및 분석한다. 실험 결과에서 제안하는 방법이 머리카락 및 얼굴 영역을 더자연스럽게 생성하고, 모자 영역의 왜곡을 성공적으로 방지했다.
Abstract
In this paper, we propose a model that performs more natural facial attribute editing by utilizing mask information in the hair and hat region. STGAN, one of state-of-the-art research of facial attribute editing, has shown results of naturally editing multiple facial attributes. However, editing hair-related attributes can produce unnatural results. The key idea of the proposed method is to additionally utilize information on the face regions that was lacking in the existing model. To do this, we apply three ideas. First, hair information is supplemented by adding hair ratio attributes through masks. Second, unnecessary changes in the image are suppressed by adding cycle consistency loss. Third, a hat segmentation network is added to prevent hat region distortion. Through qualitative evaluation, the effectiveness of the proposed method is evaluated and analyzed. The method proposed in the experimental results generated hair and face regions more naturally and successfully prevented the distortion of the hat region.
참고문헌 (17)
- I. J. Goodfellow, "Generative Adversarial Nets", Advances in neural information processing systems, pp.2672~2680 (2014)
- M. Mirza, "Conditional Generative Adversarial Nets", arXiv preprint arXiv : 1411, 1~7 (2014)
- G. Perarnau, "Invertible Conditional GANs for Image Editing", NIPS 2016Workshop on Adversarial Training, pp.1~9 (2016)
- A. B. L. Larsen, "Autoencoding Beyond Pixels using a Learned Similarity Metric", Proceedings of the 33rd International Conference on Machine Learning, 48, pp.1~9 (2016)
- Zhenliang He, "AttGAN: Facial Attribute Editing by Only Changing What You Want", IEEE Transactions on Image Processing, 28(11), pp.5464~5478 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- M. Liu, "STGAN : A Unified Selective Transfer Network for Arbitrary Image Attribute Editing", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3673~3682 (2019)
- W. Shen, "Learning Residual Images for Face Attribute Manipulation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4030~4038 (2017)
- G. Zhang, "Generative Adversarial Network with Spatial Attention for Face Attribute Editing", Proceedings of the European Conference on Computer Vision (ECCV), pp.417~432 (2018)
- H. S. Yang, "Study on Performance Improvement of SAGAN using Mask", Proceeding of 2019 Korea Signal Processing Conference, pp.2557~2560 (2019)
- H. S. Yang, "Face Attribute Editing using AttGAN and Guide Mask", 2019 International Conference on Electronics, Information, and Communication (ICEIC), pp.1~3 (2019)
- P. Chen, "Facial Attribute Editing using Semantic Segmentation", 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), pp.97~103 (2019)
- J. Y. Zhu, "Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks", Proceedings of the IEEE international conference on computer vision, pp.2223~2232 (2017)
- P. Isola, "Image-to-Image Translation with Conditional Adversarial Networks", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.1125~1134 (2017)
- Y. Choi, "StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.8789~8797 (2018)
- X. Zheng, "A Survey to Deep Facial Attribute Analysis", International Journal of Computer Vision, pp.1~33 (2020)
- Z. Liu, "Deep Learning Face Attributes in the Wild", Proceedings of the IEEE International Conference on Computer Vision, pp.3730~3738 (2015)
- C. H. Lee, "MaskGAN : Towards Diverse and Interactive Facial Image Manipulation", arXiv preprint arXiv : 1907. 11922v2, 1~20 (2020)