Deep image prior
Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a gene...
主要な著者: | Ulyanov, D, Vedaldi, A, Lempitsky, V |
---|---|
フォーマット: | Journal article |
言語: | English |
出版事項: |
Springer
2020
|
類似資料
-
Deep image prior
著者:: Ulyanov, D, 等
出版事項: (2018) -
Texture networks: Feed-forward synthesis of textures and stylized images
著者:: Ulyanov, D, 等
出版事項: (2016) -
It takes (only) two: adversarial generator-encoder networks
著者:: Ulyanov, D, 等
出版事項: (2018) -
Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis
著者:: Ulyanov, D, 等
出版事項: (2017) -
Deep learning with physical and power-spectral priors for robust image inversion
著者:: Deng, Mo,Ph. D.Massachusetts Institute of Technology.
出版事項: (2020)