National Science Foundation of China [U20B2072, 61976137]; Shanghai Jiao Tong University Medical Engineering Cross Research [YG2021ZD18]
机构署名:
本校为通讯机构
摘要:
Shape primitives decomposition has been an important and long-standing task in 3D shape analysis. Prior arts heavily rely on 3D point clouds or voxel data for shape primitives extraction, which are less practical in real-world scenarios. This paper proposes to learn shape primitives from multi-view images by introducing implicit surface rendering. It is challenging since implicit shapes have a high degree of freedom, which violates the simplicity property of shape primitives. In this work, a novel regularization term named Implicit Convexity Regularization (ICR) imposed on implicit primitive l...