MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
This enables deployment of high-fidelity generative models on edge devices, addressing a bottleneck for mobile and embedded applications.
The paper tackled the high computational complexity of style-based GANs for image synthesis by proposing MobileStyleGAN, which reduces parameters by 3.5x and computational complexity by 9.5x compared to StyleGAN2 while maintaining comparable quality.
In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fewer parameters and is x9.5 less computationally complex than StyleGAN2, while providing comparable quality.