Semantic Image Inpainting with Deep Generative Models
Citations
4,404 citations
2,447 citations
1,800 citations
1,789 citations
1,606 citations
References
111,197 citations
"Semantic Image Inpainting with Deep..." refers methods in this paper
...For training the DCGAN model, we follow the training procedure in [32] and use Adam [15] for optimization....
[...]
...We use Adam for optimization and restrict z to [−1, 1] in each iteration, which we observe to produce more stable results....
[...]
40,609 citations
38,211 citations
"Semantic Image Inpainting with Deep..." refers background in this paper
...Generative Adversarial Networks (GANs) are a framework for training generative parametric models, and have been shown to produce high quality images [9, 4, 32]....
[...]
..., in our case an adversarial network [9, 32], is trained, we search for an encoding of the corrupted image that is “closest” to the image in the latent space....
[...]
30,124 citations
"Semantic Image Inpainting with Deep..." refers methods in this paper
...3; we visualize the latent manifold, using t-SNE [25] on the 2-dimensional space, and the intermediate results in the optimization steps of finding ẑ....
[...]
20,769 citations
"Semantic Image Inpainting with Deep..." refers background in this paper
...Autoencoders and Variational Autoencoders (VAEs) [16] have become a popular approach to learning of complex distributions in an unsupervised setting....
[...]