Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

Published in NeurIPS 2020 Deep Inverse Workshop [Paper]

Citation: Joseph Dean, Giannis Daras , Alexandros G. Dimakis, "Intermediate Layer Optimization for Inverse Problems using Deep Generative Models", NeurIPS 2020 Deep Inverse Workshop

We propose Intermediate Layer Optimization, a novel optimization algorithm for solving inverse problems with deep generative models. Instead of optimizing only over the initial latent code, we progressively change the input layer we optimize over, obtaining successively more expressive generators. We also experiment with different loss functions and utilize a perceptual loss combined with standard mean squared error. We empirically show that our approach outperforms the state-of-the-art inversion methods introduced in StyleGAN-2 and PULSE.