Timezone: »

Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
Gauri Jagatap · Chinmay Hegde

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #41

Deep neural networks as image priors have been recently introduced for problems such as denoising, super-resolution and inpainting with promising performance gains over hand-crafted image priors such as sparsity. Unlike learned generative priors they do not require any training over large datasets. However, few theoretical guarantees exist in the scope of using untrained network priors for inverse imaging problems. We explore new applications and theory for untrained neural network priors. Specifically, we consider the problem of solving linear inverse problems, such as compressive sensing, as well as non-linear problems, such as compressive phase retrieval. We model images to lie in the range of an untrained deep generative network with a fixed seed. We further present a projected gradient descent scheme that can be used for both compressive sensing and phase retrieval and provide rigorous theoretical guarantees for its convergence. We also show both theoretically as well as empirically that with deep neural network priors, one can achieve better compression rates for the same image quality as compared to when hand crafted priors are used.

Author Information

Gauri Jagatap (Iowa State University)

Graduate student at Iowa State University

Chinmay Hegde (New York University)

More from the Same Authors