AmbientFlow: Invertible generative models from incomplete, noisy measurements
This work addresses a bottleneck in imaging science by enabling generative model training from limited data, though it is incremental as it builds on existing flow-based and variational Bayesian methods.
The paper tackles the problem of training flow-based generative models when only noisy and incomplete measurements are available, which is common in computed imaging, and demonstrates that AmbientFlow effectively learns object distributions and improves image reconstruction.
Generative models have gained popularity for their potential applications in imaging science, such as image reconstruction, posterior sampling and data sharing. Flow-based generative models are particularly attractive due to their ability to tractably provide exact density estimates along with fast, inexpensive and diverse samples. Training such models, however, requires a large, high quality dataset of objects. In applications such as computed imaging, it is often difficult to acquire such data due to requirements such as long acquisition time or high radiation dose, while acquiring noisy or partially observed measurements of these objects is more feasible. In this work, we propose AmbientFlow, a framework for learning flow-based generative models directly from noisy and incomplete data. Using variational Bayesian methods, a novel framework for establishing flow-based generative models from noisy, incomplete data is proposed. Extensive numerical studies demonstrate the effectiveness of AmbientFlow in learning the object distribution. The utility of AmbientFlow in a downstream inference task of image reconstruction is demonstrated.