Image Restoration using Autoencoding Priors

Abstract

We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vector, that is, the distance to the local mean, as the negative log likelihood of our natural image prior. For image restoration, we maximize the likelihood using gradient descent by backpropagating the autoencoder error. A key advantage of our approach is that we do not need to train separate networks for different image restoration tasks, such as non-blind deconvolution with different kernels, or super-resolution at different magnification factors. We demonstrate state of the art results for non-blind deconvolution and super-resolution using the same autoencoding prior.

Cited by in corpus (12)

• Denoising Prior Driven Deep Neural Network for Image Restoration
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
• Gradient Step Denoiser for convergent Plug-and-Play
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• Joint Intensity-Gradient Guided Generative Modeling for Colorization
• Algorithms and software for projections onto intersections of convex and non-convex sets with applications to inverse problems
• MeanShift++: Extremely Fast Mode-Seeking With Applications to Segmentation and Object Tracking
• Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
• Learning Priors in High-frequency Domain for Inverse Imaging Reconstruction
• A Deep Optimization Approach for Image Deconvolution
• Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face