Deep Learning Practice · End Term · 13 Sept 2026 · May 2026 term · Set 1

Question 30: SRGAN performs photo-realistic super-resolution using a …

Question 30

+2 marksOne or more correct options

SRGAN performs photo-realistic super-resolution using a GAN. Which of the following statements are correct?

Select all that apply.

A
Its perceptual loss combines a content loss and an adversarial loss, rather than relying on pixel-wise MSE alone.
B
The content loss is computed on feature maps of a pre-trained VGG network (perceptual similarity), not purely in pixel space.
C
Purely MSE-optimized solutions tend to be overly smooth because they approximate a pixel-wise average of many plausible HR solutions, losing high-frequency texture.
D
The adversarial term makes SRGAN maximize PSNR, which is why it always achieves a higher PSNR than the MSE-based SRResNet.

Show answer

Correct answers

A
Its perceptual loss combines a content loss and an adversarial loss, rather than relying on pixel-wise MSE alone.
B
The content loss is computed on feature maps of a pre-trained VGG network (perceptual similarity), not purely in pixel space.
C
Purely MSE-optimized solutions tend to be overly smooth because they approximate a pixel-wise average of many plausible HR solutions, losing high-frequency texture.

See the whole paper Take it as a mock test

Question 30 of 31 in the IIT Madras BS Deep Learning Practice (Deep Learning Practice) End Term paper sat on 13 Sept 2026, in the May 2026 term (Deep Learning Practice 13 Sep 26 (Session 2)). It carries 2 marks.

Question 30: SRGAN performs photo-realistic super-resolution using a …

Question 30

More questions from this paper