E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

TL;DR

E2Style introduces a new feed-forward network for StyleGAN inversion that significantly improves efficiency and quality, enabling real image editing with results comparable to optimization-based methods.

Contribution

The paper proposes E2Style, a novel inversion network with multi-scale, multi-loss, and multi-stage features that outperforms existing forward-based methods and rivals optimization-based approaches.

Findings

E2Style achieves better inversion quality than existing forward-based methods.

E2Style's results are comparable to state-of-the-art optimization-based methods.

The method enables effective real image editing applications.

Abstract

This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks. The goal of StyleGAN inversion is to find the exact latent code of the given image in the latent space of StyleGAN. This problem has a high demand for quality and efficiency. Existing optimization-based methods can produce high-quality results, but the optimization often takes a long time. On the contrary, forward-based methods are usually faster but the quality of their results is inferior. In this paper, we present a new feed-forward network "E2Style" for StyleGAN inversion, with significant improvement in terms of efficiency and effectiveness. In our inversion network, we introduce: 1) a shallower backbone with multiple efficient heads across scales; 2) multi-layer identity loss and multi-layer face parsing loss to the loss function; and 3) multi-stage refinement. Combining these designs together forms an effective and efficient method that exploits all benefits of optimization-based and forward-based methods. Quantitative and qualitative results show that our E2Style performs better than existing forward-based methods and comparably to state-of-the-art optimization-based methods while maintaining the high efficiency as well as forward-based methods. Moreover, a number of real image editing applications demonstrate the efficacy of our E2Style. Our code is available at \url{https://github.com/wty-ustc/e2style}