SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder

arXiv:2403.17502v1 Announce Type: new
Abstract: The data bottleneck has emerged as a fundamental challenge in learning based image restoration methods. Researchers have attempted to generate synthesized training data using paired or unpaired samples to address this challenge. This study proposes SeNM-VAE, a semi-supervised noise modeling method that leverages both paired and unpaired datasets to generate realistic degraded data. Our approach is based on modeling the conditional distribution of degraded and clean images with a specially designed graphical model. Under the …

abstract arxiv autoencoder challenge cs.cv data generate hierarchical image image restoration modeling noise researchers samples semi-supervised study synthesized training training data type vae