论文标题
3D网状重建的网状先验
Meshlet Priors for 3D Mesh Reconstruction
论文作者
论文摘要
从一组无序的稀疏，嘈杂的3D点估算网格是一个具有挑战性的问题，需要精心选择的先验。现有的手工制作的先验（例如平滑性正规机）在减弱噪音和保留当地细节之间实施了不良的权衡。最近的深度学习方法直接从数据中学习先验，从而产生了令人印象深刻的结果。但是，先验是在对象级别上学习的，这使得这些算法特定于阶级，甚至对对象的姿势敏感。我们介绍了网格，用来学习局部形状先验的小斑点。网格充当局部特征的字典，因此允许使用学习的先验在任何姿势和看不见的类中重建对象网格，即使噪声很大并且样品稀疏。
Estimating a mesh from an unordered set of sparse, noisy 3D points is a challenging problem that requires carefully selected priors. Existing hand-crafted priors, such as smoothness regularizers, impose an undesirable trade-off between attenuating noise and preserving local detail. Recent deep-learning approaches produce impressive results by learning priors directly from the data. However, the priors are learned at the object level, which makes these algorithms class-specific and even sensitive to the pose of the object. We introduce meshlets, small patches of mesh that we use to learn local shape priors. Meshlets act as a dictionary of local features and thus allow to use learned priors to reconstruct object meshes in any pose and from unseen classes, even when the noise is large and the samples sparse.
