PhD student Varun Kelkar presented in ICML 2021 on “Prior Image-Constrained Reconstruction using Style-Based Generative Models”.

Our new #ICML2021 paper talks about a new formulation of a classical problem, where a “prior image” is used to help solve highly ill-posed imaging inverse problems. Basically, we use StyleGANs and the style-separation it provides to measure the difference between the sought-after and the prior image, and then formulate a constrained optimization problem in […]