A method for face image inpainting based on generative adversarial networks: [a thesis submitted to Auckland University of Technology in partial fulfilment of the requirements for the degree of Master of Computer and Information Sciences (MCIS), 2022] / Xinyi Gao ; supervisor: Wei Qi Yan.
Recently, face image inpainting has become a fascinating research area in the field of deep learning. However, the existing methods have the disadvantage that the image inpainting results are not clear enough. Therefore, we propose a new face image inpainting method based on GAN (Generative Adversar...
Saved in:
| Main Author: | |
|---|---|
| Corporate Author: | |
| Format: | Ethesis |
| Language: | English |
| Subjects: | |
| Online Access: | Click here to access this resource online |
| Summary: | Recently, face image inpainting has become a fascinating research area in the field of deep learning. However, the existing methods have the disadvantage that the image inpainting results are not clear enough. Therefore, we propose a new face image inpainting method based on GAN (Generative Adversarial Network) in this thesis. Firstly, a deformation network based on GAN is designed. Then we add an identical autoencoder to the generative part of this generative adversarial network. Two loss functions of mean square error (MSE) loss and GAN loss are combined in the training process. Finally, through the analysis of results based on the CelebA dataset, the average of the new model's PSNR (Peak Signal-to-Noise Ratio) is 36.74dB, the average value of SSIM (Structural SIMilarity) is 0.91. Compared with the previous method, the new model has improved the effect of face image inpainting. Author supplied keywords: Face Image Inpainting; Generative Adversarial Network; Convolutional Neural Network; Autoencoder. |
|---|---|
| Physical Description: | 1 online resource |
| Bibliography: | Includes bibliographical references. |