A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

2022/10/24 by Matthew C Bendel, Bendel, Matthew, R. Badlishah Ahmad +3 · 3 citations
Computer Science · #Advanced Image Processing Techniques #Medical Image Segmentation Techniques #Generative Adversarial Networks and Image Synthesis

paper · doi:10.48550/arxiv.2210.13389

Abstract

penalty and an adaptively weighted standard-deviation reward. Using quantitative evaluation metrics like conditional Fréchet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and large-scale inpainting applications. The code for our model can be found here: https://github.com/matt-bendel/rcGAN.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Perception-Distortion Tradeoff

Cited by

• Self-Supervised Learning from Noisy and Incomplete Data
• Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurements
• Conditional Flow Matching for Bayesian Posterior Inference

Related

• pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
• Medical image reconstruction with image-adaptive priors learned by use of generative adversarial networks
• Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction
• Learning from small data sets: Patch-based regularizers in inverse problems for image reconstruction
• Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction