Collaborative Learning for Faster StyleGAN Embedding
This work addresses the speed bottleneck for researchers and practitioners using StyleGAN for image editing, though it is incremental as it builds on existing optimization methods.
The paper tackles the efficiency problem of embedding images into StyleGAN's latent space for semantic editing by proposing a collaborative learning framework that combines an embedding network with an optimization-based iterator, achieving high-quality results with a single forward pass.
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.