当前位置:
X-MOL 学术
›
Comput. Graph. Forum
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Towards Light‐Weight Portrait Matting via Parameter Sharing
Computer Graphics Forum ( IF 2.5 ) Pub Date : 2020-11-26 , DOI: 10.1111/cgf.14179 Yutong Dai 1 , Hao Lu 1 , Chunhua Shen 1
Computer Graphics Forum ( IF 2.5 ) Pub Date : 2020-11-26 , DOI: 10.1111/cgf.14179 Yutong Dai 1 , Hao Lu 1 , Chunhua Shen 1
Affiliation
Traditional portrait matting methods typically consist of a trimap estimation network and a matting network. Here, we propose a new light‐weight portrait matting approach, termed parameter‐sharing portrait matting (PSPM). Different from conventional portrait matting models where the encoder and decoder networks in two tasks are often separately designed, here a single encoder is employed for the two tasks in PSPM, while each task still has its task‐specific decoder. Thus, the role of the encoder is to extract semantic features and two decoders function as a bridge between low‐resolution feature maps generated by the encoder and high‐resolution feature maps for pixel‐wise classification/regression. In particular, three variants capable of implementing the parameter‐sharing portrait matting network are proposed and investigated, respectively. As demonstrated in our experiments, model capacity and computation costs can be reduced significantly, by up to and , respectively, with PSPM, whereas the matting accuracy only slightly deteriorates. In addition, qualitative and quantitative evaluations show that sharing the encoder is an effective way to achieve portrait matting with limited computational budgets, indicating a promising direction for applications of real‐time portrait matting on mobile devices.
中文翻译:
通过参数共享实现轻量人像抠像
传统的肖像抠图方法通常由三图估计网络和抠图网络组成。在这里,我们提出了一种新的轻量级肖像抠像方法,称为参数共享肖像抠像(PSPM)。与传统的肖像抠像模型不同,后者通常会分别设计两个任务中的编码器和解码器网络,此处PSPM中的两个任务使用单个编码器,而每个任务仍具有特定于任务的解码器。因此,编码器的作用是提取语义特征,而两个解码器则充当编码器生成的低分辨率特征图与高分辨率特征图之间的桥梁,以进行像素分类/回归。特别是,分别提出和研究了能够实现参数共享人像抠图网络的三个变体。和分别使用PSPM时,消光精度只会稍微降低。此外,定性和定量评估表明,共享编码器是在有限的计算预算下实现人像抠像的有效方法,这为在移动设备上实时人像抠像的应用指明了一个有希望的方向。
更新日期:2020-11-26
中文翻译:
通过参数共享实现轻量人像抠像
传统的肖像抠图方法通常由三图估计网络和抠图网络组成。在这里,我们提出了一种新的轻量级肖像抠像方法,称为参数共享肖像抠像(PSPM)。与传统的肖像抠像模型不同,后者通常会分别设计两个任务中的编码器和解码器网络,此处PSPM中的两个任务使用单个编码器,而每个任务仍具有特定于任务的解码器。因此,编码器的作用是提取语义特征,而两个解码器则充当编码器生成的低分辨率特征图与高分辨率特征图之间的桥梁,以进行像素分类/回归。特别是,分别提出和研究了能够实现参数共享人像抠图网络的三个变体。和分别使用PSPM时,消光精度只会稍微降低。此外,定性和定量评估表明,共享编码器是在有限的计算预算下实现人像抠像的有效方法,这为在移动设备上实时人像抠像的应用指明了一个有希望的方向。