arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05815cs.CV
收藏

MulayCap:使用单目摄像机的多层次人的行为捕获

MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera

Tsinghua University(清华大学);The University of Hong Kong(香港大学)

Zhaoqi Su, Weilin Wan, Tao Yu, Lingjie Liu, Lu Fang, Wenping Wang, Yebin Liu

摘要:

我们介绍MulayCap,一种新的人类表演捕捉方法,使用单目视频摄像机,而不需要预扫描。该方法使用“多层”表示的几何重建和纹理渲染,分别。对于几何重建,我们分解成多个几何层,即人体网格层和服装片层的穿着人。背后的关键技术是一个服装从视频(GfV)的方法,用于优化服装的形状和重建的动态布料,以适应输入的视频序列,基于布料模拟模型,这是有效地解决了梯度下降。对于纹理渲染,我们将每个输入图像帧分解为一个着色层和一个纹理层,并提出了一种方法,用于融合一个固定的纹理映射和解决详细的服装几何使用着色层。与现有的单视图人类表现捕获系统相比,我们的“多层”方法绕过了繁琐和耗时的扫描步骤,以获得人类特定的网格模板。实验结果表明,MulayCap产生逼真的渲染动态变化的细节,还没有实现在任何以前的单目视频摄像机系统。受益于其完全语义建模,MulayCap可以应用于各种重要的编辑应用,如布料编辑,重定位,重新照明和AR应用。

英文摘要:

We introduce MulayCap, a novel human performance capture method using a monocular video camera without the need for pre-scanning. The method uses "multi-layer" representations for geometry reconstruction and texture rendering, respectively. For geometry reconstruction, we decompose the clothed human into multiple geometry layers, namely a body mesh layer and a garment piece layer. The key technique behind is a Garment-from-Video (GfV) method for optimizing the garment shape and reconstructing the dynamic cloth to fit the input video sequence, based on a cloth simulation model which is effectively solved with gradient descent. For texture rendering, we decompose each input image frame into a shading layer and an albedo layer, and propose a method for fusing a fixed albedo map and solving for detailed garment geometry using the shading layer. Compared with existing single view human performance capture systems, our "multi-layer" approach bypasses the tedious and time consuming scanning step for obtaining a human specific mesh template. Experimental results demonstrate that MulayCap produces realistic rendering of dynamically changing details that has not been achieved in any previous monocular video camera systems. Benefiting from its fully semantic modeling, MulayCap can be applied to various important editing applications, such as cloth editing, re-targeting, relighting, and AR applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑