Fig. 1. DnCNN’s architecture. 그림 1. DnCNN 구조
Fig. 2. Proposed network’s architecture. 그림 2. 제안하는 network 구조
Fig. 3. ResNet team’s full pre-activation. 그림 3. ResNet team의 full pre-activation
Fig. 4. Low frequency component. 그림 4. Low frequency 성분
Fig. 5. Overall data flow. 그림 5. 전반적인 데이터 흐름
Fig. 6. DnCNN’s denoising result. 그림 6. DnCNN의 denoising 결과
Fig. 7. Proposed network’s result. 그림 7. 제안하는 network의 결과
Table 1. The PSNR according to subtraction. 표 1. 감산 여부에 따른 PSNR
Table 2. The PSNR of each training method. 표 2. 학습방법에 따른 PSNR 결과
참고문헌
- Jeon, Yougn-Eun, et al. "Gaussian Noise Reduction Algorithm using Self-similarity," Journal of the Institute of Electronics Engineers of Korea SP, 44, 5, 1-10, 2007.
- Multimedia Laboratory, "Large-scale CelebFaces Attributes (CelebA) Dataset," https://mmlab.ie.cuhk.edu.hk
- Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L, "Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising," IEEE Transactions on Image Processing, 26, 7, 3142-3155, 2017. DOI:10.1109/TIP.2017.2662206
- He, K., Zhang, X., Ren, S., & Sun, J, "Deep residual learning for image recognition," In Proceedings of the IEEE conference on computer vision and pattern recognition. 770-778, 2016.
- He, K., Zhang, X., Ren, S., & Sun, J., "Identity mappings in deep residual networks," In European conference on computer vision, (2016, October), 630-645.