论文标题
矩阵Fisher分布的概率定向估计
Probabilistic orientation estimation with matrix Fisher distributions
论文作者
论文摘要
本文着重于使用深神经网络对3D旋转（$ so（3）$）的概率分布进行估算。由于$ \ mathbb {r}^n $和$ so（3）$之间的拓扑差异，因此在拓扑差异上，学习将模型回归旋转集很困难。我们通过使用神经网络来输出矩阵Fisher分布的参数来克服此问题，因为这些参数是同型至$ \ Mathbb {r}^9 $。通过对此分布使用负的对数似然损失，我们将获得相对于网络输出的损失。通过优化这种损失，我们可以改善几个具有挑战性的数据集，即Pascal3d+，ModelNet10- $ SO（3）$和UPNA HEAD POSE。
This paper focuses on estimating probability distributions over the set of 3D rotations ($SO(3)$) using deep neural networks. Learning to regress models to the set of rotations is inherently difficult due to differences in topology between $\mathbb{R}^N$ and $SO(3)$. We overcome this issue by using a neural network to output the parameters for a matrix Fisher distribution since these parameters are homeomorphic to $\mathbb{R}^9$. By using a negative log likelihood loss for this distribution we get a loss which is convex with respect to the network outputs. By optimizing this loss we improve state-of-the-art on several challenging applicable datasets, namely Pascal3D+, ModelNet10-$SO(3)$ and UPNA head pose.
