StyleGAN-based CLIP-guided Image Shape Manipulation

被引:0
作者
Qian, Yuchen [1 ]
Yamamoto, Kohei [1 ]
Yanai, Keiji [1 ]
机构
[1] Univ Electrocommun, Tokyo, Japan
来源
19TH INTERNATIONAL CONFERENCE ON CONTENT-BASED MULTIMEDIA INDEXING, CBMI 2022 | 2022年
关键词
GANs; text-guided image manipulation; image-text cross-modal model; CLIP;
D O I
10.1145/3549555.3549556
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a text-guided image manipulation method which focuses on editing shape attribute using text description. We combine an image generation model, StyleGAN2, and image-text matching model, CLIP, and we have achieved the goal of image shape attribute manipulation by modifying the parameters of the pretrained StyleGAN2 generator. Qualitative and quantitative evaluations are conducted to demonstrate the effectiveness of the proposed method.
引用
收藏
页码:162 / 166
页数:5
相关论文
共 29 条
  • [1] Abdal Rameen, 2022, SIGGRAPH22 Conference Proceeding: Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings, DOI 10.1145/3528233.3530747
  • [2] StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows
    Abdal, Rameen
    Zhu, Peihao
    Mitra, Niloy J.
    Wonka, Peter
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (03):
  • [3] Bau D, 2021, Arxiv, DOI arXiv:2103.10951
  • [4] Bau David, 2020, P EUR C COMP VIS
  • [5] Navigating the GAN Parameter Space for Semantic Image Editing
    Cherepkov, Anton
    Voynov, Andrey
    Babenko, Artem
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 3670 - 3679
  • [6] Choi Y, 2020, PROC CVPR IEEE, P8185, DOI 10.1109/CVPR42600.2020.00821
  • [7] Semantic Image Synthesis via Adversarial Learning
    Dong, Hao
    Yu, Simiao
    Wu, Chao
    Guo, Yike
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : CP1 - CP38
  • [8] Gal R, 2021, Arxiv, DOI arXiv:2108.00946
  • [9] Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
  • [10] Haonan Qiu, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12359), P19, DOI 10.1007/978-3-030-58568-6_2