Dense Reconstruction Using 3D Object Shape Priors
Dense Reconstruction Using 3D Object Shape Priors
复制标题
DOI：
10.1109/cvpr.2013.170
复制
发表时间：
2013-06
期刊：
影响因子：
--
通讯作者：
Amaury Dame;V. Prisacariu;C. Ren;I. Reid
中科院分区：
文献类型：
--
作者：
Amaury Dame;V. Prisacariu;C. Ren;I. Reid
我们提出了一种结合实时密集重建和基于形状先验的三维跟踪与重建的单目SLAM算法。当前的实时密集SLAM方法仅限于可见表面的重建。此外，它们中的大多数都是基于照片一致性误差的最小化，这通常使它们对投机行为敏感。在3D姿态恢复文献中，利用先验形状知识来处理图像信息不完善和模糊带来的问题。同时，深度传感器的成功也表明，结合关节图像和深度信息大大提高了经典单目三维跟踪和三维重建方法的稳健性。在这项工作中，我们将密集SLAM与3D对象姿势和形状恢复联系起来。更具体地说，我们使用特定于对象的身份以及场景中已知类别的对象(S)的6D姿势和额外的形状自由度自动增强SLAM系统，结合图像数据和深度信息进行姿势和形状恢复。这导致了一种系统，该系统允许利用从场景中分割的已知对象(S)进行全尺寸3D重建。分割提高了密集SLAM系统构建的地图的清晰度、准确性和完整性，而密集的3D数据有助于分割过程，产生比仅使用2D图像数据更快和更可靠的收敛。
We propose a formulation of monocular SLAM which combines live dense reconstruction with shape priors-based 3D tracking and reconstruction. Current live dense SLAM approaches are limited to the reconstruction of visible surfaces. Moreover, most of them are based on the minimisation of a photo-consistency error, which usually makes them sensitive to specularities. In the 3D pose recovery literature, problems caused by imperfect and ambiguous image information have been dealt with by using prior shape knowledge. At the same time, the success of depth sensors has shown that combining joint image and depth information drastically increases the robustness of the classical monocular 3D tracking and 3D reconstruction approaches. In this work we link dense SLAM to 3D object pose and shape recovery. More specifically, we automatically augment our SLAM system with object specific identity, together with 6D pose and additional shape degrees of freedom for the object(s) of known class in the scene, combining image data and depth information for the pose and shape recovery. This leads to a system that allows for full scaled 3D reconstruction with the known object(s) segmented from the scene. The segmentation enhances the clarity, accuracy and completeness of the maps built by the dense SLAM system, while the dense 3D data aids the segmentation process, yielding faster and more reliable convergence than when using 2D image data alone.