RankSRGAN uses a learned ranking network as a differentiable surrogate for perceptual metrics, enabling GAN-based super-resolution to be optimized directly toward NIQE, Ma, or PI.
Ntire 2017 challenge on single image super-resolution: Dataset and study
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution
RankSRGAN uses a learned ranking network as a differentiable surrogate for perceptual metrics, enabling GAN-based super-resolution to be optimized directly toward NIQE, Ma, or PI.