October 17, 2018,
Posted by Heuna Kim
Link:Paper
Main Contribution
- SRResNet : set a new best benchmark result for SISR for PSNR measure
- SRGAN:
- Content loss: a variant of pixel-wise loss depending on the network feature map
- Adversarial loss: the probability of the discriminator over all training samples \[ l_{Gen}^{SR} = \sum_{n=1}^N - log D_{\theta_D}(G_{\theta_G}(I^{LR})) \]
- GAN based minmax between generated and original \[ \min_{\theta_G} \max_{\theta_D} E_{I^{HR} \sim p_{train}(I^{HR})} [\log D_{\theta_D}(I^{HR})] + E_{I^{LR} \sim p_G(I^{LR})} [\log(1- D_{\theta_D}(G_{\theta_G}(I^{HR})))] \]
- performance improvement on MOS testing by a far margin
Relevant Terminologies to understand
- perceptual similarity
- SSIM - structural similarity
- PSNR - peak signal-to-noise ratio
- MOS - mean opinion score
- Wilcoxon signed-rank tests
- Parametric ReLu
Interesting Relevant Work
Site created with