A Generic Approach for Enhancing GANs by Regularized Latent Optimization

TL;DR

This paper introduces a generic framework that enhances pre-trained GANs by inferring optimal latent distributions through Wasserstein gradient flow, improving various image generation tasks without retraining.

Contribution

It proposes a novel, efficient latent optimization method for enhancing pre-trained GANs across multiple applications without additional training.

Findings

Effective in image generation and editing tasks

Outperforms existing methods in quality and efficiency

Versatile across different application scenarios

Abstract

With the rapidly growing model complexity and data volume, training deep generative models (DGMs) for better performance has becoming an increasingly more important challenge. Previous research on this problem has mainly focused on improving DGMs by either introducing new objective functions or designing more expressive model architectures. However, such approaches often introduce significantly more computational and/or designing overhead. To resolve such issues, we introduce in this paper a generic framework called {\em generative-model inference} that is capable of enhancing pre-trained GANs effectively and seamlessly in a variety of application scenarios. Our basic idea is to efficiently infer the optimal latent distribution for the given requirements using Wasserstein gradient flow techniques, instead of re-training or fine-tuning pre-trained model parameters. Extensive experimental results on applications like image generation, image translation, text-to-image generation, image inpainting, and text-guided image editing suggest the effectiveness and superiority of our proposed framework.