资源分类
》 资源 》论文》Laplacian Meshes for Monocular 3D Shape Recovery*

Laplacian Meshes for Monocular 3D Shape Recovery*

2020-04-02 | |  63 |   51 |   0

Abstract

We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a well-posed problem. Furthermore, this does not require any training data and elim- inates the need to pre-align the reference shape with the one to be re- constructed, as was done in earlier methods.

上一篇：Using Linking Features in Learning Non-parametric Part Models

下一篇：Joint Face Alignment: Rescue Bad Alignments with Good Ones by Regularized Re-fitting

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...