Implementation of a Vision-Mamba network, integrating State Space Models (SSM) with a patch-based encoder–decoder for image inpainting, colorization, and denoising. Trained with L1, SSIM, and VGG perceptual losses to preserve both structure and perceptual realism.
computer-vision deep-learning pytorch autoencoder ssm image-inpainting denoising-autoencoders image-restoration state-space-model ssim-loss perceptual-loss image-reconstructions vision-mamba mamba-block vgg-perceptual-loss
-
Updated
Nov 26, 2025 - Jupyter Notebook