论文标题
重建，栅格和后退：来自单个图像的致密形状和姿势估计
Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image
论文作者
论文摘要
本文提出了一个新的系统，以获得密集的对象重建以及单个图像的6-DOF姿势。朝着高保真重建的旨在，最近的几种方法利用隐式表面表示和深度神经网络来估计一个对象的3D网格，给定一个图像。但是，所有此类方法仅恢复对象的形状。重建通常在规范框架中，不适合下游机器人技术任务。为此，我们利用了可区分渲染的最新进展（尤其是栅格化），以在相机框架中使用3D重建来关闭循环。我们证明了我们的方法 - 与先前的ART相比，被称为重建，栅格化和反向Prop（RRB）的姿势估计错误明显降低，并且能够从图像中恢复密集的对象形状和姿势。我们将结果进一步扩展到（离线）设置，在该设置中，我们展示了一个密集的单眼型eGomotion估计系统。
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. Geared towards high fidelity reconstruction, several recent approaches leverage implicit surface representations and deep neural networks to estimate a 3D mesh of an object, given a single image. However, all such approaches recover only the shape of an object; the reconstruction is often in a canonical frame, unsuitable for downstream robotics tasks. To this end, we leverage recent advances in differentiable rendering (in particular, rasterization) to close the loop with 3D reconstruction in camera frame. We demonstrate that our approach---dubbed reconstruct, rasterize and backprop (RRB) achieves significantly lower pose estimation errors compared to prior art, and is able to recover dense object shapes and poses from imagery. We further extend our results to an (offline) setup, where we demonstrate a dense monocular object-centric egomotion estimation system.
