Double Blind Imaging with Generative Modeling

2025-03-27

AI Summary

This paper addresses the inverse problem of blind image deconvolution—recovering sharp images from noisy, degraded observations under *doubly-blind* conditions: both the imaging system parameters (e.g., point spread function, PSF) and paired image-measurement data are entirely unknown. We propose the first generative framework extending AmbientGAN to doubly-blind imaging, which jointly models the distribution of unpaired clean images and their degraded observations to implicitly learn a prior over PSFs. Our method integrates generative modeling, diffusion-based posterior sampling, and model-driven reconstruction, enabling fully unsupervised, unpaired end-to-end blind deconvolution. Experiments demonstrate accurate learning of Gaussian and motion blur priors; our approach significantly outperforms prior-free classical methods across diverse blind deconvolution benchmarks and achieves state-of-the-art reconstruction quality.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Blind inverse problems in imaging arise from uncertainties in the system used to collect (noisy) measurements of images. Recovering clean images from these measurements typically requires identifying the imaging system, either implicitly or explicitly. A common solution leverages generative models as priors for both the images and the imaging system parameters (e.g., a class of point spread functions). To learn these priors in a straightforward manner requires access to a dataset of clean images as well as samples of the imaging system. We propose an AmbientGAN-based generative technique to identify the distribution of parameters in unknown imaging systems, using only unpaired clean images and corrupted measurements. This learned distribution can then be used in model-based recovery algorithms to solve blind inverse problems such as blind deconvolution. We successfully demonstrate our technique for learning Gaussian blur and motion blur priors from noisy measurements and show their utility in solving blind deconvolution with diffusion posterior sampling.

Problem

• Solving blind inverse problems in imaging with uncertainties
• Recovering clean images without paired training data
• Learning imaging system priors for blind deconvolution

Innovation

• AmbientGAN-based generative technique for system identification
• Uses unpaired clean images and corrupted measurements
• Learns parameter distribution for model-based recovery