论文标题
PNP-NET：混合视角N点网络
PnP-Net: A hybrid Perspective-n-Point Network
论文作者
论文摘要
我们使用将深度学习与基于模型的算法相结合的混合方法来考虑强大的透视N点（PNP）问题。 PNP是估计世界上一组3D点及其相应的2D投影的校准相机姿势的问题。在其更具挑战性的强大版本中，某些对应关系可能不匹配，并且必须有效丢弃。经典的解决方案通过迭代鲁棒的非线性最小二乘法解决了PNP，该方法利用了问题的几何形状，但在计算上是不准确的或计算密集的。相比之下，我们建议将深度学习初始阶段结合起来，然后结合基于模型的微调阶段。这种由PNP-NET表示的混合方法成功地估算了在对应误差和噪声下的未知姿势参数，具有低和固定的计算复杂性要求。我们证明了它在合成数据和现实世界数据上的优势。
We consider the robust Perspective-n-Point (PnP) problem using a hybrid approach that combines deep learning with model based algorithms. PnP is the problem of estimating the pose of a calibrated camera given a set of 3D points in the world and their corresponding 2D projections in the image. In its more challenging robust version, some of the correspondences may be mismatched and must be efficiently discarded. Classical solutions address PnP via iterative robust non-linear least squares method that exploit the problem's geometry but are either inaccurate or computationally intensive. In contrast, we propose to combine a deep learning initial phase followed by a model-based fine tuning phase. This hybrid approach, denoted by PnP-Net, succeeds in estimating the unknown pose parameters under correspondence errors and noise, with low and fixed computational complexity requirements. We demonstrate its advantages on both synthetic data and real world data.
