In class tools:
Image processing techniques - We applied different types of noise to the images which falls under image processing.
Studying system properties - The code uses PSNR (Peak Signal-to-Noise Ratio) to measure the performance of different denoising techniques, effectively analyzing the quality and behavior of the applied systems.
Low pass filters - We use LPF's in bilateral and gaussian filtering by attenuating high frequency components while preserving lower frequency components like smooth regions.
Processing the signal in a different basis: In wavelet denoising, the wavelet transform processes the image in the wavelet basis, allowing efficient noise separation and detail preservation.
Out of class tools:
MPRNet - the model we used as our final method, uses an encoder-decoder architecture and neural networks to reweight local features to produce a denoised image.