Education, Science, Technology, Innovation and Life
Open Access
Sign In

HCM: Icon art design based on diffusion model

Download as PDF

DOI: 10.23977/jaip.2024.070404 | Downloads: 8 | Views: 583

Author(s)

Yekuan He 1, Peiqi Yuan 2

Affiliation(s)

1 Institute of International Education, Guangzhou College of Technology and Business, Foshan, 528100, China
2 Physics Department, Capital Normal University, Beijing, 100080, China

Corresponding Author

Yekuan He

ABSTRACT

With the advancement of AI-generated image technology, the field of icon design has increasingly incorporated computational methods as design references. Compared to direct design by human designers, AI technology can significantly reduce time and labor costs. In response to this, this research propose the High-Quality Customized Model (HCM) for controllable stylized icon design. This research introduce the Icon-ControlNet module to achieve precise control over icon generation, ensuring high levels of customization. Additionally, article employ the IconIC module to reduce computational resource consumption and enhance generation efficiency. This article have also constructed the IconData dataset, comprising 25,000 finely annotated medium-sized images. Through extensive ablation experiments, the results were evaluated by FID and IS, effectively demonstrating the advantages of HCM in terms of icon clarity, style transfer, and diversity. This model provides a novel solution for the automation and personalization of icon design.

KEYWORDS

Diffusion model, Icon Design, HCM model, Image Generation

CITE THIS PAPER

Yekuan He, Peiqi Yuan, HCM: Icon art design based on diffusion model. Journal of Artificial Intelligence Practice (2024) Vol. 7: 25-36. DOI: http://dx.doi.org/10.23977/jaip.2024.070404.

REFERENCES

[1] Zhou T , Li Q , Lu H ,et al.GAN review: Models and medical image fusion applications[J].Information Fusion, 2023.
[2] Child R. Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images[J]. 2020. DOI: 10.48550/arXiv.2011.10650.
[3] Chen J, Pan Y, Yao T, et al. Controlstyle: Text-driven stylized image generation using diffusion priors[C]// Proceedings of the 31st ACM International Conference on Multimedia. 2023: 7540-7548.
[4] Ruiz N, Li Y, Jampani V, et al. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023: 22500-22510.
[5] Kingma D P, Welling M .Auto-Encoding Variational Bayes[J].arXiv.org, 2014.DOI:10.48550/arXiv.1312.6114.
[6] Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models[J]. Advances in neural information processing systems, 2020, 33: 6840-6851.
[7] Sohl-Dickstein J, Weiss E, Maheswaranathan N, et al. Deep unsupervised learning using nonequilibrium thermodynamics[C]//International conference on machine learning. PMLR, 2015: 2256-2265.
[8] Cong Zhao, Pinghua Chen. Icon Shape Generation Based on Generative Adversarial Network[J]. Computer Science and Application , 2020, 10(3): 456-463. https://doi.org/10.12677/CSA.2020.103047
[9] Zhang L, Rao A, Agrawala M. Adding conditional control to text-to-image diffusion models[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 3836-3847.
[10] Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C]// International conference on machine learning. PMLR, 2021: 8748-8763.
[11] Gafni O, Polyak A, Ashual O, et al. Make-a-scene: Scene-based text-to-image generation with human priors[C]// European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 89-106.
[12] Avrahami O, Hayes T, Gafni O, et al. Spatext: Spatio-textual representation for controllable image generation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 18370-18380.
[13] Lin J, Jiang Z, Guo J, et al. IconDM: Text-Guided Icon Set Expansion Using Diffusion Models[C]//ACM Multimedia 2024.
[14] Vaswani A. Attention is all you need[J]. arXiv preprint arXiv:1706.03762, 2017.
[15] Canny J. A computational approach to edge detection[J]. IEEE Transactions on pattern analysis and machine intelligence, 1986 (6): 679-698.

Downloads: 13811
Visits: 413574

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.