FISTNet: FusIon of STyle-path generative Networks for Facial Style Transfer

TL;DR

FISTNet is a novel facial style transfer network that fuses multiple styles efficiently using pre-trained styleGANs, requiring limited data and preserving facial identity and details.

Contribution

The paper introduces FISTNet, a multipath style fusion network that leverages pre-trained styleGANs and residual modulation to enable high-quality facial style transfer with limited data.

Findings

FISTNet outperforms existing methods in style transfer quality.

The approach requires less training data than traditional methods.

FISTNet effectively fuses multiple styles in a single output.

Abstract

With the surge in emerging technologies such as Metaverse, spatial computing, and generative AI, the application of facial style transfer has gained a lot of interest from researchers as well as startups enthusiasts alike. StyleGAN methods have paved the way for transfer-learning strategies that could reduce the dependency on the huge volume of data that is available for the training process. However, StyleGAN methods have the tendency of overfitting that results in the introduction of artifacts in the facial images. Studies, such as DualStyleGAN, proposed the use of multipath networks but they require the networks to be trained for a specific style rather than generating a fusion of facial styles at once. In this paper, we propose a FusIon of STyles (FIST) network for facial images that leverages pre-trained multipath style transfer networks to eliminate the problem associated with lack of huge data volume in the training phase along with the fusion of multiple styles at the output. We leverage pre-trained styleGAN networks with an external style pass that use residual modulation block instead of a transform coding block. The method also preserves facial structure, identity, and details via the gated mapping unit introduced in this study. The aforementioned components enable us to train the network with very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient, flexible style and model fusion in the generative space. We perform extensive experiments to show the superiority of FISTNet in comparison to existing state-of-the-art methods.