论文标题
快速点特征嵌入的不规则成制的MLP
Irregularly Tabulated MLP for Fast Point Feature Embedding
论文作者
论文摘要
为了在测试时针对点功能嵌入的急剧加速，我们提出了一个新框架，该框架使用一对多层感知器（MLP）和查找表（LUT）将点坐标转换为高维特征。与PointNet的功能嵌入了需要数百万个点产品的PointNet功能嵌入部分相比，在测试时间内提议的框架不需要这样的矩阵矢量产品层，但只需要从成列表的MLP中查找最近的实体，然后插入插入，然后在3D lattice intoputs上进行插入，这是对3D lattice lattice neclate in Bective nective new lattice new lattsectional intaint of Intapt的基本安排。我们将此框架称为LUTI-MLP：LUT插值ML，该框架提供了一种训练端到端不规则列表的MLP的方法，以特定方式耦合到LUT，而无需在测试时进行任何近似值。 LUTI-MLP还为嵌入功能的Jacobian计算WRT全局姿势坐标提供了显着加速，测试时可以用于点集注册问题。在使用ModelNet40进行了广泛的评估之后，我们确认LUTI-MLP即使使用很小的（例如$ 4^3 $）的晶格也可以产生与MLP相当的性能，同时实现了显着的速度：嵌入的$ 100 \ timper $ $ timper $ for Empted $ $ $ 12 \ tims $ $ $ $ $ $ $ $ $ $ $ 860的$ $ $ $ $ $ $ $ $ $ $ $ $ $。
Aiming at drastic speedup for point-feature embeddings at test time, we propose a new framework that uses a pair of multi-layer perceptrons (MLP) and a lookup table (LUT) to transform point-coordinate inputs into high-dimensional features. When compared with PointNet's feature embedding part realized by MLP that requires millions of dot products, the proposed framework at test time requires no such layers of matrix-vector products but requires only looking up the nearest entities from the tabulated MLP followed by interpolation, defined over discrete inputs on a 3D lattice that is substantially arranged irregularly. We call this framework LUTI-MLP: LUT Interpolation ML that provides a way to train end-to-end irregularly tabulated MLP coupled to a LUT in a specific manner without the need for any approximation at test time. LUTI-MLP also provides significant speedup for Jacobian computation of the embedding function wrt global pose coordinate on Lie algebra $\mathfrak{se}(3)$ at test time, which could be used for point-set registration problems. After extensive evaluation using the ModelNet40, we confirmed that the LUTI-MLP even with a small (e.g., $4^3$) lattice yields performance comparable to that of the MLP while achieving significant speedup: $100\times$ for the embedding, $12\times$ for the approximate Jacobian, and $860\times$ for the canonical Jacobian.
