Statistical Edge Detection And UDF Learning For Shape Representation

arXiv:2405.03381v1 Announce Type: cross
Abstract: In the field of computer vision, the numerical encoding of 3D surfaces is crucial. It is classical to represent surfaces with their Signed Distance Functions (SDFs) or Unsigned Distance Functions (UDFs). For tasks like representation learning, surface classification, or surface reconstruction, this function can be learned by a neural network, called Neural Distance Function. This network, and in particular its weights, may serve as a parametric and implicit representation for the surface. The network must …

abstract arxiv classification computer computer vision cs.cv cs.lg detection edge encoding function functions numerical representation representation learning stat.ap statistical surface tasks type vision