Bernoulli Embedding Model and Its Application in Texture Mapping

Abstract

A novel texture mapping technique is proposed based on nonlinear dimension reduction, called Bernoulli logistic embedding (BLE). Our probabilistic embedding model builds texture mapping with minimal shearing effects. A log-likelihood function, related to the Bregman distance, is used to measure the similarity between two related matrices defined over the spaces before and after embedding. Low-dimensional embeddings can then be obtained through minimizing this function by a fast block relaxation algorithm. To achieve better quality of texture mapping, the embedded results are adopted as initial values for mapping enhancement by stretch-minimizing. Our method can be applied to both complex mesh surfaces and dense point clouds.