Abstract
Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) algorithms based on the real-time requirements. Recently, with the advent of Convolutional Neural Networks (CNNs) researchers have explored the possibility of using machine learning techniques to reconstruct the 3D structure of a scene and jointly predict the camera pose. In this work, we present a framework that achieves state-of-the-art performance on single image depth prediction for both indoor and outdoor scenes. The depth prediction system is then extended to predict optical flow and ultimately the camera pose and trained end-to-end. Our motion estimation framework outperforms the previous motion prediction systems and we also demonstrate that the state-of-the-art metric depths can be further improved using the knowledge of pose.
Abstract (translated)
给定图像对或图像序列的恢复结构和运动参数是计算机视觉中充分研究的问题。这通常通过采用基于实时要求的运动结构(SfM)或同时定位和映射(SLAM)算法来实现。最近,随着卷积神经网络(CNN)的出现,研究人员探索了使用机器学习技术重建场景的3D结构并联合预测相机姿势的可能性。在这项工作中,我们提出了一个框架,在室内和室外场景的单个图像深度预测上实现了最先进的性能。然后扩展深度预测系统以预测光流并最终预测相机姿势并进行端到端训练。我们的运动估计框架优于先前的运动预测系统,并且我们还证明了使用姿势知识可以进一步提高最先进的度量深度。
URL
https://arxiv.org/abs/1807.05705