论文标题
实时高分辨率背景垫
Real-Time High-Resolution Background Matting
论文作者
论文摘要
我们引入了一种实时高分辨率的替换技术，该技术以4K分辨率为30fps，在现代GPU上以60fps运行。我们的技术基于背景垫子，其中捕获了背景的附加框架，并用于恢复Alpha Matte和前景层。主要的挑战是计算高质量的α哑光，在实时处理高分辨率图像的同时，保留了链级的头发细节。为了实现这一目标，我们采用了两个神经网络。基本网络计算一个低分辨率结果，该结果通过在选择性补丁上高分辨率运行的第二个网络来完善。我们介绍了两个LargesCale视频和图像垫数据集：Videomatte240K和Photomatte13k/85。与以前的背景垫子中的先前最先进的方法相比，我们的方法会产生更高的质量结果，同时在速度和分辨率方面产生了巨大的提升。
We introduce a real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is based on background matting, where an additional frame of the background is captured and used in recovering the alpha matte and the foreground layer. The main challenge is to compute a high-quality alpha matte, preserving strand-level hair details, while processing high-resolution images in real-time. To achieve this goal, we employ two neural networks; a base network computes a low-resolution result which is refined by a second network operating at high-resolution on selective patches. We introduce two largescale video and image matting datasets: VideoMatte240K and PhotoMatte13K/85. Our approach yields higher quality results compared to the previous state-of-the-art in background matting, while simultaneously yielding a dramatic boost in both speed and resolution.
