Super-resolution basics in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Super-resolution basics

Which metric matters for Super-resolution and WHY

For super-resolution, we want to measure how close the enhanced image is to the original high-quality image. Common metrics are PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index).

PSNR measures the difference in pixel values; higher PSNR means less error. SSIM measures how similar the structure and textures are; higher SSIM means better visual quality. These metrics matter because super-resolution aims to restore details and sharpness, not just reduce pixel errors.

Confusion matrix or equivalent visualization

Super-resolution is a regression task, not classification, so confusion matrix does not apply.

Instead, we use example images and metric scores like:

Original Image (High-res)
  |
Low-res Image (Input)
  |
Super-resolved Image (Output)

Metrics:
PSNR = 30 dB (higher is better)
SSIM = 0.85 (range 0 to 1, higher is better)
    

Precision vs Recall tradeoff equivalent

In super-resolution, the tradeoff is between sharpness and noise/artifacts.

If the model tries too hard to sharpen details, it may add fake textures or noise (over-sharpening). If it is too smooth, details are lost (under-sharpening).

Good super-resolution balances detail recovery (high SSIM) with low noise (high PSNR).

What "good" vs "bad" metric values look like

Good super-resolution:

• PSNR above 30 dB (less pixel error)
• SSIM above 0.8 (high structural similarity)
• Visual output looks clear and natural without strange artifacts

Bad super-resolution:

• PSNR below 25 dB (high pixel error)
• SSIM below 0.6 (poor structural similarity)
• Output looks blurry or has unnatural textures

Common pitfalls in super-resolution metrics

• Relying only on PSNR: High PSNR does not always mean better visual quality because it ignores perceptual details.
• Ignoring visual inspection: Metrics can miss artifacts that look bad to humans.
• Overfitting to training images: Model may memorize details and score high on metrics but fail on new images.
• Data leakage: Using test images during training inflates metric scores falsely.

Self-check question

Your super-resolution model has a PSNR of 32 dB but an SSIM of 0.55. Is it good?

Answer: Not really. The PSNR is good, meaning pixel differences are low, but the low SSIM shows the structure and textures are not well preserved. The output might look blurry or unnatural. You should improve the model to increase SSIM for better visual quality.

Key Result

PSNR and SSIM are key metrics; high PSNR means less pixel error, high SSIM means better visual similarity.