GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion
复制标题
GarmentNets：通过规范空间形状完成对服装进行类别级姿势估计
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Shuran Song
中科院分区：
文献类型：
--
作者：
Cheng Chi;Shuran Song
本文处理的任务类别级姿态估计的服装。由于几乎无限的自由度，服装的完整配置（即，姿态）通常由其整个3D表面的逐顶点3D位置来描述。然而，服装通常也会受到自遮挡的极端情况的影响，特别是在折叠或起皱时，这使得感知其完整的3D表面变得具有挑战性。为了解决这些挑战，我们提出了GarmentNets，其关键思想是将可变形对象的姿态估计问题制定为规范空间中的形状完成任务。该规范空间是在类别内的服装实例之间定义的，因此，指定了共享的类别级姿势。通过将观察到的部分表面映射到规范空间并在该空间中完成它，输出表示使用具有逐顶点规范坐标标签的完整3D网格来描述服装的完整配置。为了正确处理薄的3D结构上的服装，我们提出了一种新的3D形状表示使用广义缠绕数字段。实验表明，GarmentNets是能够推广到看不见的服装实例，并实现显着更好的性能相比，其他方法。代码和数据可以在https://garmentnets.cs.columbia.edu中找到。
This paper tackles the task of category-level pose estimation for garments. With a near infinite degree of freedom, a garment’s full configuration (i.e., poses) is often described by the per-vertex 3D locations of its entire 3D surface. However, garments are also commonly subject to extreme cases of self-occlusion, especially when folded or crumpled, making it challenging to perceive their full 3D surface. To address these challenges, we propose GarmentNets, where the key idea is to formulate the deformable object pose estimation problem as a shape completion task in the canonical space. This canonical space is defined across garments instances within a category, therefore, specifies the shared category-level pose. By mapping the observed partial surface to the canonical space and completing it in this space, the output representation describes the garment’s full configuration using a complete 3D mesh with the per-vertex canonical coordinate label. To properly handle the thin 3D structure presented on garments, we proposed a novel 3D shape representation using the generalized winding number field. Experiments demonstrate that GarmentNets is able to generalize to unseen garment instances and achieve significantly better performance compared to alternative approaches. Code and data can be found in https://garmentnets.cs.columbia.edu.
DOI：
10.1109/cvpr.2019.00275
发表时间：
2019-01
期刊：
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子：
--
作者：
He Wang;Srinath Sridhar;Jingwei Huang;Julien P. C. Valentin;Shuran Song;L. Guibas
通讯作者：
He Wang;Srinath Sridhar;Jingwei Huang;Julien P. C. Valentin;Shuran Song;L. Guibas