Neural Cages for Detail-Preserving 3D Deformations

In the paper, we detailed two applications of our method: stock amplification and deformation transfer. In this document, we provide additional results for each application. Stock amplification via deformation. In Table 1 , 2 and 3 we show the entire deformation results from the chair, table and car categories. As mentioned in the main paper, the test sets consist of 100 pairs of unseen source and target shapes randomly sampled from ShapeNet dataset [2].