Laser & Optoelectronics Progress, Volume. 60, Issue 4, 0410017(2023)
Lightweight Cartoonlization Method Based on Generative Adversarial Network
Fig. 1. Image animation stylization framework
Fig. 2. Surface representation
Fig. 3. Structure representation
Fig. 4. Texture representation
Fig. 5. Main structure of the generative network
Fig. 6. Each module structure of the generative network. (a) Conv_Block; (b) DSConv; (c) IRB; (d) Down-Conv; (e) Up-Conv
Fig. 7. Discriminant network structure
Fig. 8. Convergence of loss functions
Fig. 9. Comparison of subjective effects of image animation stylization
Fig. 10. Experimental results of three animation styles and comparison between proposed method and CartoonGAN
Fig. 11. Results of proposed method in different scenarios
Fig. 12. Ablation study
|
|
|
Get Citation
Copy Citation Text
Jinguang Sun, Wei Wang. Lightweight Cartoonlization Method Based on Generative Adversarial Network[J]. Laser & Optoelectronics Progress, 2023, 60(4): 0410017
Category: Image Processing
Received: Dec. 2, 2021
Accepted: Jan. 5, 2022
Published Online: Feb. 14, 2023
The Author Email: Wang Wei (1803671965@qq.com)