Haolin Jia
Haolin Jia joined Google in Jun 2022, as the member of Core ML On-Device Solutions (Xeno) team, led by Matthias Grundmann. His works mainly focus on the image/video generation and real-time editing, using model compression and distillation strategy to enable the model inference run on-device with the high performance.
His area of interest includes computer vision and graphics, especially the cutting-edge generative AI techniques.
Research Areas
Authored Publications
Sort By
BlazeStyleGAN: A Real-Time On-Device StyleGAN
Fei Deng
Lu Wang
Chuo-Ling Chang
Tingbo Hou
(2023)
Preview abstract
StyleGAN models have been widely adopted for generating and editing face images. Yet, few work investigated running StyleGAN models on mobile devices. In this work, we introduce BlazeStyleGAN --- to the best of our knowledge, the first StyleGAN model that can run in real-time on smartphones. We design an efficient synthesis network with the auxiliary head to convert features to RGB at each level of the generator, and only keep the last one at inference. We also improve the distillation strategy with a multi-scale perceptual loss using the auxiliary heads, and an adversarial loss for the student generator and discriminator. With these optimizations, BlazeStyleGAN can achieve real-time performance on high-end mobile GPUs. Experimental results demonstrate that BlazeStyleGAN generates high-quality face images and even mitigates some artifacts from the teacher model.
View details
