Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

TL;DR

This paper introduces pixel2style2pixel (pSp), a versatile encoder framework that embeds real images into StyleGAN's latent space for efficient, multi-modal image-to-image translation without adversarial training.

Contribution

The paper presents a novel encoder that directly maps images into StyleGAN's extended latent space, enabling flexible and simplified image translation tasks.

Findings

Encoder can embed real images into W+ without optimization

Framework supports multi-modal synthesis through style resampling

Effective on various facial translation tasks and extendable beyond faces

Abstract

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our pSp framework is based on a novel encoder network that directly generates a series of style vectors which are fed into a pretrained StyleGAN generator, forming the extended W+ latent space. We first show that our encoder can directly embed real images into W+, with no additional optimization. Next, we propose utilizing our encoder to directly solve image-to-image translation tasks, defining them as encoding problems from some input domain into the latent domain. By deviating from the standard invert first, edit later methodology used with previous StyleGAN encoders, our approach can handle a variety of tasks even when the input image is not represented in the StyleGAN domain. We show that solving translation tasks through StyleGAN significantly simplifies the training process, as no adversary is required, has better support for solving tasks without pixel-to-pixel correspondence, and inherently supports multi-modal synthesis via the resampling of styles. Finally, we demonstrate the potential of our framework on a variety of facial image-to-image translation tasks, even when compared to state-of-the-art solutions designed specifically for a single task, and further show that it can be extended beyond the human facial domain.