Performance Analysis of Virtual Human Bodies with Clothing and Hair from Images to Animation
2018 ◽
Vol 8
(6)
◽
pp. 69
Keyword(s):
Virtual human bodies, clothing, and hair are widely used in a number of scenarios such as 3D animated movies, gaming, and online fashion. Machine learning can be used to construct data-driven 3D human bodies, clothing, and hair. In this thesis, we provide a solution to 3D shape and pose estimation under the most challenging situation where only a single image is available and the image is captured in a natural environment with unknown camera calibration. We also demonstrate that a simplified 2D clothing model helps to increase the accuracy of 2D body shape estimation significantly.
2020 ◽
pp. 169-179
2020 ◽
Vol 24
(04)
◽
pp. 1153-1157
Keyword(s):
2020 ◽
Vol 9
(10)
◽
pp. 8207-8215
Keyword(s):
Keyword(s):