BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes
BaRe-ESA: A Riemannian Framework for Unregistered Human Body Shapes
复制标题
DOI：
10.1109/iccv51070.2023.01304
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
Emmanuel Hartman;E. Pierson;Martin Bauer;N. Charon;M. Daoudi
中科院分区：
文献类型：
--
作者：
Emmanuel Hartman;E. Pierson;Martin Bauer;N. Charon;M. Daoudi
我们提出了一种新的黎曼框架，用于人体扫描表示、插值和外推。BaRe-ESA直接在未注册的网格上操作，即不需要建立先前的点对点对应关系或假设一致的网格结构。我们的方法依赖于一个潜在空间表示，它配备了一个黎曼（非欧几里德）度量，该度量与曲面空间上的不变高阶度量相关联。在FAUST和DFAUST数据集上的实验结果表明，BaRe-ESA在形状配准、插值和外推方面都比以前的解决方案有了显著的改进。我们的模型的效率和强度在运动传递和身体形状和姿势的随机生成等应用中得到了进一步的证明。
We present Basis Restricted Elastic Shape Analysis (BaRe-ESA), a novel Riemannian framework for human body scan representation, interpolation and extrapolation. BaRe-ESA operates directly on unregistered meshes, i.e., without the need to establish prior point to point correspondences or to assume a consistent mesh structure. Our method relies on a latent space representation, which is equipped with a Riemannian (non-Euclidean) metric associated to an invariant higher-order metric on the space of surfaces. Experimental results on the FAUST and DFAUST datasets show that BaRe-ESA brings significant improvements with respect to previous solutions in terms of shape registration, interpolation and extrapolation. The efficiency and strength of our model is further demonstrated in applications such as motion transfer and random generation of body shape and pose.