论文标题
使用DSAC从RGB和RGB-D图像重新定位的视觉摄像头重新定位
Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC
论文作者
论文摘要
我们描述了一个基于学习的系统，该系统估算了相对于已知环境的单个输入图像的摄像机位置和方向。该系统是灵活的W.R.T.测试时和培训时可用的信息量，可满足不同的应用程序。输入图像可以是RGB-D或RGB，并且可以将环境的3D模型用于训练，但不是必需的。在最小情况下，我们的系统仅需要RGB图像和地面真相在训练时构成，并且在测试时仅需要一个RGB图像。该框架由深层神经网络和完全可区分的姿势优化组成。神经网络预测所谓的场景坐标，即输入图像与环境3D场景空间之间的密集对应关系。姿势优化使用可区分的RANSAC（DSAC）实现了姿势参数的可靠拟合，以促进端到端训练。该系统是DSAC ++的扩展，并称为DSAC*，它实现了最先进的精度，以基于RGB的重新定位为基于RGB的各种公共数据集，以及基于RGB-D的重新定位的竞争精度。
We describe a learning-based system that estimates the camera position and orientation from a single input image relative to a known environment. The system is flexible w.r.t. the amount of information available at test and at training time, catering to different applications. Input images can be RGB-D or RGB, and a 3D model of the environment can be utilized for training but is not necessary. In the minimal case, our system requires only RGB images and ground truth poses at training time, and it requires only a single RGB image at test time. The framework consists of a deep neural network and fully differentiable pose optimization. The neural network predicts so called scene coordinates, i.e. dense correspondences between the input image and 3D scene space of the environment. The pose optimization implements robust fitting of pose parameters using differentiable RANSAC (DSAC) to facilitate end-to-end training. The system, an extension of DSAC++ and referred to as DSAC*, achieves state-of-the-art accuracy an various public datasets for RGB-based re-localization, and competitive accuracy for RGB-D-based re-localization.
