Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
This work addresses the problem of improving reconstruction accuracy for inverse problems using generative models, but it is incremental as it builds on existing inversion algorithms.
The paper tackles the challenge of representation error in GAN-based inverse problem solving by proposing a regularized training method for intermediate layers, which results in lower reconstruction errors across various under-sampling ratios in compressed sensing, inpainting, and super-resolution tasks.
Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation error, the fundamental limitation of the network in representing any particular signal. Recently, multiple proposed inversion algorithms reduce representation error by optimizing over intermediate layer representations. These methods are typically applied to generative models that were trained agnostic of the downstream inversion algorithm. In our work, we introduce a principle that if a generative model is intended for inversion using an algorithm based on optimization of intermediate layers, it should be trained in a way that regularizes those intermediate layers. We instantiate this principle for two notable recent inversion algorithms: Intermediate Layer Optimization and the Multi-Code GAN prior. For both of these inversion algorithms, we introduce a new regularized GAN training algorithm and demonstrate that the learned generative model results in lower reconstruction errors across a wide range of under sampling ratios when solving compressed sensing, inpainting, and super-resolution problems.