Collaborative Learning for Faster StyleGAN Embedding

TL;DR

This paper introduces a collaborative learning framework combining an embedding network and an optimization iterator to efficiently embed images into StyleGAN's latent space, improving speed and quality.

Contribution

It proposes a novel collaborative learning approach that enhances embedding efficiency and quality for StyleGAN by integrating a learned network with an optimization process.

Findings

Achieves high-quality embeddings with a single network pass

Significantly improves embedding speed over traditional optimization methods

Demonstrates effectiveness across various experiments

Abstract

The latent code of the recent popular model StyleGAN has learned disentangled representations thanks to the multi-layer style-based generator. Embedding a given image back to the latent space of StyleGAN enables wide interesting semantic image editing applications. Although previous works are able to yield impressive inversion results based on an optimization framework, which however suffers from the efficiency issue. In this work, we propose a novel collaborative learning framework that consists of an efficient embedding network and an optimization-based iterator. On one hand, with the progress of training, the embedding network gives a reasonable latent code initialization for the iterator. On the other hand, the updated latent code from the iterator in turn supervises the embedding network. In the end, high-quality latent code can be obtained efficiently with a single forward pass through our embedding network. Extensive experiments demonstrate the effectiveness and efficiency of our work.