Real-Time Portrait Stylization on the Edge
This work addresses the problem of efficient and fast portrait stylization for mobile users, representing an incremental improvement in optimization for edge deployment.
The paper tackled real-time portrait stylization on mobile devices by proposing a latency-driven differentiable architecture search method, achieving a 10x computation reduction and enabling real-time video stylization on smartphones.
In this work we demonstrate real-time portrait stylization, specifically, translating self-portrait into cartoon or anime style on mobile devices. We propose a latency-driven differentiable architecture search method, maintaining realistic generative quality. With our framework, we obtain $10\times$ computation reduction on the generative model and achieve real-time video stylization on off-the-shelf smartphone using mobile GPUs.