Various problems existed in the image inpainting algorithms, which can't meet people's requirements visually. Aiming at the defects of the existing image inpainting algorithms, such as low accuracy, poor visual consistency, and unstable training, an improved image inpainting algorithm used on a multi-scale generative adversarial network (GAN) and neighbourhood model have been proposed in the paper. The proposed algorithm mainly improves the network structure of the discriminator, and introduces a multi-scale discriminator based on the global discriminator and the local discriminator. The multi-scale discriminators were trained on images of different resolutions. Discriminators of different scales have different receptive fields, which can guide the generator to generate more global image views and finer details. Aiming at the problem of gradient disappearance or gradient explosion that often occurs in GAN training, the method of WGAN (Wasserstein GAN) has been used to simulate the sample data distribution using EM distance. The proposed model has been trained and tested on the CelebA, ImageNet, and Place2. The experimental results show that compared with the previous algorithm model, the proposed algorithm improves the accuracy of image inpainting and can generate more realistic repairing images, and it is suitable for many types of images.
We consider a massively parallel implementation of Richardson-Lucy or maximum likelihood restoration with a spatially-variant point spread function (PSF). Richardson-Lucy iterates involve the computation of sums of the form: where O(x'
q
) is the incident optical field estimate at discrete source location x'
q
, I(x
q
) is the measured discrete image at discrete field location x
q
, and P(x
q
, x'
q
) is the discrete PSF – the probability that a photon from source region x'
q
is incident on the detector at field region x
q
. In general P is a function of source and field coordinates, and the computational burden of Eq. 1 is intractably large.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.