3D pose transfer is one of the most challenging 3D generation tasks. It aims to transfer the pose of a source mesh to a target mesh and keep the identity (e.g., body shape) of the target mesh. Some previous works require key point annotations to build reliable correspondence between the source and target meshes, while other methods do not consider any shape correspondence between sources and targets, which leads to limited generation quality. In this work, we propose a correspondence-refinement network to help the 3D pose transfer for both human and animal meshes. The correspondence between source and target meshes is first established by solving an optimal transport problem. Then, we warp the source mesh according to the dense correspondence and obtain a coarse warped mesh. The warped mesh will be better refined with our proposed \textit{Elastic Instance Normalization}, which is a conditional normalization layer and can help to generate high-quality meshes. Extensive experimental results show that the proposed architecture can effectively transfer the poses from source to target meshes and produce better results with satisfied visual performance than state-of-the-art methods.
翻译:3D 配置配置是3D 最具有挑战性的 3D 生成任务之一。 它旨在将源网格的外形转换到目标网格, 并保持目标网格的身份( 如身体形状 ) 。 一些先前的作品需要关键点说明, 以便在源和目标网目之间建立可靠的对应关系, 而其他方法并不考虑源和目标之间任何形状的对应关系, 导致生成质量有限 。 在这项工作中, 我们提议一个通信改进网络, 帮助 3D 既为人类也为动物网目进行转移。 源网和目标网目之间的通信首先通过解决一个最佳的运输问题来建立 。 然后, 我们根据密集的通信对源网格进行扭曲, 并获得一个粗略的扭曲网目。 扭曲网格将用我们提议的 \ textit{ Elacincinalizalization} 改进, 因为它是一个有条件的常规层, 有助于生成高品质的 meshes。 广泛的实验结果显示, 拟议的架构可以有效地将配置从源区划转移到目标, 并产生比状态方法更满意的视觉效果更好的结果 。