LiveCap: Real-time Human Performance Capture from Monocular Video

TOG 2019 GVV

亮点:

1)实时,25Hz;对松弛的衣物也进行了重建。

2)skeleton pose estimation时,加入了face landmark;silhouette alignment时,用的是图像距离变换。

3)surface registration时,利用了texture信息;基于部件进行silhouette alignment。

LiveCap: Real-time Human Performance Capture from Monocular Video_第1张图片

 

LiveCap: Real-time Human Performance Capture from Monocular Video_第2张图片

 

LiveCap: Real-time Human Performance Capture from Monocular Video_第3张图片

 

 

 

你可能感兴趣的:(论文阅读,human,reconstruction)