3D Pose Transfer with Correspondence Learning and Mesh Refinement
This addresses the problem of generating realistic 3D meshes with transferred poses for applications in animation and modeling, though it is incremental as it builds on existing methods.
The paper tackles 3D pose transfer by proposing a correspondence-refinement network that establishes dense correspondence via optimal transport and refines meshes with Elastic Instance Normalization, achieving better results than state-of-the-art methods with improved visual performance.
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 achieve 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 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.