Learning to Super-Resolve Blurry Face and Text Images
Citations
837 citations
Cites background or methods from "Learning to Super-Resolve Blurry Fa..."
...[63] propose a multi-class GAN-based FH model composed of a generic generator and class-specific discriminators....
[...]
..., PSNR) but far exceeding others in terms of perceptual quality, in which case the MOS testing is the most reliable IQA method for accurately measuring the perceptual quality [8], [25], [46], [62], [63], [64], [65]....
[...]
...[63] incorporate a multi-class GAN consisting of a generator and multiple class-specific discriminators....
[...]
597 citations
567 citations
Cites methods from "Learning to Super-Resolve Blurry Fa..."
...Recently, CNNs have also been used for image recovering problems [4, 14, 39, 42, 43, 44]....
[...]
350 citations
Cites methods from "Learning to Super-Resolve Blurry Fa..."
...We also note that several methods develop GANs [39] to solve image deraining and image super-resolution [36]....
[...]
335 citations
Cites background from "Learning to Super-Resolve Blurry Fa..."
...Recently, deep learning has been widely used in many low-level vision problems, such as denoising [1, 20, 45], super-resolution[4, 35, 13, 14, 15, 43, 31], dehazing [27], derain/dedirt [6, 5], edge-preserving filtering [39, 18], and image deblurring (non-blind [28, 38, 44] and blind [29, 2, 42])....
[...]
References
123,388 citations
111,197 citations
"Learning to Super-Resolve Blurry Fa..." refers methods in this paper
...[34] we train the models using the Adam optimizer [19] with momentum terms β1 = 0....
[...]
73,978 citations
38,211 citations
"Learning to Super-Resolve Blurry Fa..." refers background or methods in this paper
...[13] introduce the GAN framework for training generative models that can generate realistic-looking images from random noise....
[...]
...Moreover, different from most methods based on GAN [13, 34, 6] that generate images from random noise, the input of our network is degraded images which contain substantial information for reconstruction....
[...]
...Specifically, we adopt a generative adversarial network (GAN) [13], which consists of generator and discriminator sub-networks that compete with each other....
[...]
...[13], in practice we train G to maximize log(Dθ(Gω(y))) which provides more sufficient gradients and leads to more stable solution than minimizing log(1 − Dθ(Gω(y))) in (2)....
[...]
30,843 citations