Super Resolution

Module: Computer Vision | Difficulty: Intermediate

Super-Resolution Objective

SRGAN Loss

ESRGAN Improvements

1. RRDB (Residual in Residual Dense Block) — removes batch normalization
2. Relativistic Discriminator — instead of
3. Perceptual Loss — VGG features at multiple scales

PSNR and SSIM

import torch
import torch.nn as nn

class ResidualDenseBlock(nn.Module):
    def __init__(self, nf=64, gc=32):
        super().__init__()
        self.conv1 = nn.Conv2d(nf, gc, 3, 1, 1)
        self.conv2 = nn.Conv2d(nf + gc, gc, 3, 1, 1)
        self.conv3 = nn.Conv2d(nf + 2 * gc, gc, 3, 1, 1)
        self.conv4 = nn.Conv2d(nf + 3 * gc, gc, 3, 1, 1)
        self.conv5 = nn.Conv2d(nf + 4 * gc, nf, 3, 1, 1)
        self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True)
    
    def forward(self, x):
        x1 = self.lrelu(self.conv1(x))
        x2 = self.lrelu(self.conv2(torch.cat([x, x1], 1)))
        x3 = self.lrelu(self.conv3(torch.cat([x, x1, x2], 1)))
        x4 = self.lrelu(self.conv4(torch.cat([x, x1, x2, x3], 1)))
        return self.conv5(torch.cat([x, x1, x2, x3, x4], 1)) + x

Key Takeaways

• GAN-based SR produces sharper results than PSNR-optimized methods
• ESRGAN with RRDB achieves state-of-the-art perceptual quality
• Real-world SR must handle blur, noise, and compression artifacts