The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D projections, a common strategy is to incorporate prior object knowledge into the reconstruction approach by establishing a 3D model and aligning it to the 2D image plane. However, current approaches are limited due to inadequate shape priors and the insufficiency of the derived image observations for a reliable alignment with the 3D model. The goal of this paper is to show how 3D object reconstruction can profit from a more sophisticated shape prior and from a combined incorporation of different observation types inferred from the images. We introduce a subcategory-aware deformable vehicle model that makes use of a prediction of the vehicle type for a more appropriate regularisation of the vehicle shape. A multi-branch CNN is presented to derive predictions of the vehicle type and orientation. This information is also introduced as prior information for model fitting. Furthermore, the CNN extracts vehicle keypoints and wireframes, which are well-suited for model-to-image association and model fitting. The task of pose estimation and reconstruction is addressed by a versatile probabilistic model. Extensive experiments are conducted using two challenging real-world data sets on both of which the benefit of the developed shape prior can be shown. A comparison to state-of-the-art methods for vehicle pose estimation shows that the proposed approach performs on par or better, confirming the suitability of the developed shape prior and probabilistic model for vehicle reconstruction.

对象的 3D 重建是许多高度相关的计算机视觉应用（例如移动机器人或自动驾驶）的先决条件。为了解决从 2D 投影重建 3D 对象的逆问题，一种常见的策略是通过建立 3D 模型并将其与 2D 图像平面对齐，将先验对象知识合并到重建方法中。然而，由于形状先验不足和派生图像观察不足以与 3D 模型可靠对齐，当前的方法受到限制。本文的目的是展示 3D 对象重建如何从更复杂的先验形状和从图像推断的不同观察类型的组合中获益。我们引入了一个子类别感知的可变形车辆模型，该模型利用车辆类型的预测来更适当地调整车辆形状。提出了一个多分支 CNN 来预测车辆类型和方向。该信息也被引入作为模型拟合的先验信息。此外，CNN 提取车辆关键点和线框，非常适合模型到图​​像的关联和模型拟合。姿态估计和重建的任务由通用概率模型解决。使用两个具有挑战性的现实世界数据集进行了广泛的实验，这两个数据集都可以显示已开发形状先验的好处。与最先进的车辆姿态估计方法的比较表明，所提出的方法性能相当或更好，