Online Try-On: GANs and TPS
Source abstract
Abstract
Style transfer between images has been a research direction gaining considerable attention in the field of image generation. CycleGAN is widely used because it does not require paired image data to train, which greatly reduces the cost of collecting data. In 2018, based on CycleGAN, a new model structure, InstaGAN, was proposed and then applied in the style transfer algorithm in the special part of an image we called instance. From then on, style transfer can transform the instance in the image. Based on CycleGAN and InstaGAN, we transformed the pictures in different domains combined with shape context and thin plate splines (TPS) in the present study. Based on generative adversarial networks (GANs), we designed a fusion network to optimize the results. We combined style transfer with TPS in fashion and got convincing performance by experiments and a fusion net with good performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Generative Adversarial Networks and Image Synthesis · Image Enhancement Techniques · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Donghua University
References (23)
Show source-provided references
1. Zhu Jun-Yan · 16th IEEE International Conference on Computer Vision, ICCV · 2017 · 2242
2. Mo Sangwoo · InstaGAN: Instance-aware Image-to-Image Translation · 2019
3. Ulyanov Vedaldi · Instance normalization. The missing ingredient for fast stylization. arXiv preprint · 2016
4. Goodfellow I. J · Neural Information Processing Systems · 2014 · 27
5. Miyato Takeru · arXiv: · 2018
6. 10.1109/TPAMI.2016.253733910.1109/TPAMI.2016.2537339 ↗
7. 10.1109/34.99355810.1109/34.993558 ↗
8. Mehdi Mirza, · CoRR · 2014
9. Radford A., Metz L., Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks, 2015.
10. Arjovsky M. · arXiv preprint arXiv:1701. · 2017 · 07875
11. Gulrajani Ishaan · arXiv: · 2017
12. 10.1109/ICCV.2017.30410.1109/ICCV.2017.304 ↗
13. Ledig C. · CVPR · 2017
14. Wang Xintao · ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks.
15. Chu Mengyu · Temporally Coherent GANs for Video Super-Resolution (TecoGAN).
16. Li C. · Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 2016 · 2479
17. Isola P. · CVPR · 2017
18. Long J. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 39 · 64010.1109/TPAMI.2016.2572683 ↗
19. Zhu Shizhan · Be Your Own Prada: Fashion Synthesis with Structural Coherence · 2017
20. Han X. · Viton: An image-based virtual try-on network. · 2017
21. Wang B. · Toward Characteristic-Preserving Image-based Virtual Try-On Network · 2018
22. Diederik P., Kingma and Ba Jimmy. Adam: A method for stochastic optimization. arXiv preprint. arXiv:1412.6980, 2014.
23. He K. · Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 2016 · 770