论文标题
边缘的实时肖像风格
Real-Time Portrait Stylization on the Edge
论文作者
论文摘要
在这项工作中,我们演示了实时肖像风格,特别是将自画像转化为移动设备上的动漫风格。我们提出了一种以延迟驱动的可区分架构搜索方法,以保持现实的生成质量。通过我们的框架,我们可以在生成模型上获得$ 10 \ times $计算减少,并使用移动GPU在现成的智能手机上实现实时视频风格。
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.