We propose a unified 3D flow frameworkfor joint learning of shape embedding and deformationfor different categories. Our goal is to recovershapes from imperfect point clouds by fitting thebest shape template in a shape...We propose a unified 3D flow frameworkfor joint learning of shape embedding and deformationfor different categories. Our goal is to recovershapes from imperfect point clouds by fitting thebest shape template in a shape repository afterdeformation. Accordingly, we learn a shape embeddingfor template retrieval and a flow-based network forrobust deformation. We note that the deformationflow can be quite different for different shapecategories. Therefore, we introduce a novel multi-hubmodule to learn multiple modes of deformation toincorporate such variation, providing a network whichcan handle a wide range of objects from differentcategories. The shape embedding is designed to retrievethe best-fit template as the nearest neighbor in a latentspace. We replace the standard fully connected layerwith a tiny structure in the embedding that significantlyreduces network complexity and further improvesdeformation quality. Experiments show the superiorityof our method to existing state-of-the-art methods viaqualitative and quantitative comparisons. Finally, ourmethod provides efficient and flexible deformation thatcan further be used for novel shape design.展开更多
基金supported by the National Key R&D Program of China(2020YFB1708900)the National Natural Science Foundation of China(62072271).
文摘We propose a unified 3D flow frameworkfor joint learning of shape embedding and deformationfor different categories. Our goal is to recovershapes from imperfect point clouds by fitting thebest shape template in a shape repository afterdeformation. Accordingly, we learn a shape embeddingfor template retrieval and a flow-based network forrobust deformation. We note that the deformationflow can be quite different for different shapecategories. Therefore, we introduce a novel multi-hubmodule to learn multiple modes of deformation toincorporate such variation, providing a network whichcan handle a wide range of objects from differentcategories. The shape embedding is designed to retrievethe best-fit template as the nearest neighbor in a latentspace. We replace the standard fully connected layerwith a tiny structure in the embedding that significantlyreduces network complexity and further improvesdeformation quality. Experiments show the superiorityof our method to existing state-of-the-art methods viaqualitative and quantitative comparisons. Finally, ourmethod provides efficient and flexible deformation thatcan further be used for novel shape design.
