Normal-guided Garment UV Prediction for Human Re-texturing
Normal-guided Garment UV Prediction for Human Re-texturing
复制标题
DOI：
10.1109/cvpr52729.2023.00449
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Yasamin Jafarian;Tuanfeng Y. Wang;Duygu Ceylan;Jimei Yang;N. Carr;Yi Zhou;Hyunjung Park
中科院分区：
文献类型：
--
作者：
Yasamin Jafarian;Tuanfeng Y. Wang;Duygu Ceylan;Jimei Yang;N. Carr;Yi Zhou;Hyunjung Park
衣服会经历复杂的几何变形，从而导致外观变化。为了以物理上合理的方式编辑人类视频，纹理映射不仅必须考虑由身体运动和衣服拟合引起的服装变换，而且还必须考虑其3D细粒度表面几何形状。然而，这提出了从图像或视频进行动态衣服的3D重建的新挑战。在本文中，我们表明，它是可以编辑穿着的人的图像和视频没有3D重建。我们估计一个几何感知的纹理映射之间的服装区域的图像和纹理空间，又名，UV图。我们的UV贴图被设计成通过利用从图像预测的3D表面法线来保持与底层3D表面的等距。我们的方法捕获的基本几何形状的服装在一个自我监督的方式，不需要地面实况注释的UV地图，可以很容易地扩展到预测时间相干的UV地图。我们证明，我们的方法优于国家的最先进的人类紫外线地图估计方法的真实的和合成数据。
Clothes undergo complex geometric deformations, which lead to appearance changes. To edit human videos in a physically plausible way, a texture map must take into account not only the garment transformation induced by the body movements and clothes fitting, but also its 3D fine-grained surface geometry. This poses, however, a new challenge of 3D reconstruction of dynamic clothes from an image or a video. In this paper, we show that it is possible to edit dressed human images and videos without 3D reconstruction. We estimate a geometry aware texture map between the garment region in an image and the texture space, a.k.a, UV map. Our UV map is designed to preserve isometry with respect to the underlying 3D surface by making use of the 3D surface normals predicted from the image. Our approach captures the underlying geometry of the garment in a self-supervised way, requiring no ground truth annotation of UV maps and can be readily extended to predict temporally coherent UV maps. We demonstrate that our method outperforms the state-of-the-art human UV map estimation approaches on both real and synthetic data.