Deep image prior

Last updated May 11, 2022 Edit Source

Deep Image Prior is a type of convolutional neural network used to enhance a given image with no prior training data other than the image itself. A neural network is randomly initialized and used as prior to solve inverse problems such as noise reduction, super-resolution, and inpainting. Image statistics is captured by the structure of a convolutional image generator rather than by any previously learned capabilities

• https://en.wikipedia.org/wiki/Deep_Image_Prior

• #PAPER Deep Image Prior (Ulyanov 2018)
  • https://dmitryulyanov.github.io/deep_image_prior
  • Paper explained: https://www.youtube.com/watch?v=_BPJFFkxSbw
  • #TALK Dmitry Ulyanov - Deep Image Prior
  • #CODE https://github.com/DmitryUlyanov/deep-image-prior
• #PAPER A Bayesian Perspective on the Deep Image Prior (Cheng 2019)
• #PAPER Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior (Laves 2020)
  • #TALK Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior
• #PAPER A Mean-Field Variational Inference Approach to Deep Image Prior for Inverse Problems in Medical Imaging (Tolle 2021)
  • #CODE https://github.com/maltetoelle/mfvi-dip