Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

02/15/2021 ∙ by Giannis Daras, et al. ∙ 13

We propose Intermediate Layer Optimization (ILO), 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 obtaining successively more expressive generators. To explore the higher dimensional spaces, our method searches for latent codes that lie within a small l_1 ball around the manifold induced by the previous layer. Our theoretical analysis shows that by keeping the radius of the ball relatively small, we can improve the established error bound for compressed sensing with deep generative models. We empirically show that our approach outperforms state-of-the-art methods introduced in StyleGAN-2 and PULSE for a wide range of inverse problems including inpainting, denoising, super-resolution and compressed sensing.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 7

page 8

page 16

page 17

Code Repositories

ilo

Official implementation of Intermediate Layer Optimization for Inverse Problems using Deep Generative Models


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.