arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.06465cs.CV
收藏

将目标检测数据集提升到3D

Lifting Object Detection Datasets into 3D

University of California at Berkeley(加州大学伯克利分校);Institute of Systems and Robotics, University of Coimbra(科英布拉大学系统与机器人研究所);Anthropics;University College London(伦敦大学学院)

Joao Carreira, Sara Vicente, Lourdes Agapito, Jorge Batista

摘要:

虽然近年来数据已经成为计算机视觉的中心,但在某些情况下仍然很难获得。特别是,获取2D图像中描绘的对象的地面真实3D形状仍然是一项具有挑战性的壮举,这阻碍了从单个图像进行基于轮廓的对象重建的进展。在这里,我们建议绕过以前的解决方案,如3D扫描或手动设计,这些解决方案的规模很小,而是用密集的、每个对象的3D重建来半自动地填充对象类别检测数据集,这些重建来自:(i)类标签,(ii)地面真值图形-地面分割和(iii)一小组关键点注释。我们提出的算法首先估计相机的观点,使用刚性结构从运动,然后重建对象的形状,通过优化的视觉外壳建议引导松散的类内形状相似性假设。视觉外壳采样过程试图将对象的投影锥与从某些有利位置拍摄的其他类似对象的最小子集的锥相交。我们表明,我们的方法能够产生令人信服的每个对象的3D重建,并准确地估计相机的观点,现有的最具挑战性的对象类别检测数据集之一,PASCAL VOC。我们希望我们的研究结果将重新激发兴趣的联合对象识别和三维重建从一个单一的图像。

英文摘要:

While data has certainly taken the center stage in computer vision in recent years, it can still be difficult to obtain in certain scenarios. In particular, acquiring ground truth 3D shapes of objects pictured in 2D images remains a challenging feat and this has hampered progress in recognition-based object reconstruction from a single image. Here we propose to bypass previous solutions such as 3D scanning or manual design, that scale poorly, and instead populate object category detection datasets semi-automatically with dense, per-object 3D reconstructions, bootstrapped from:(i) class labels, (ii) ground truth figure-ground segmentations and (iii) a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion and then reconstructs object shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions. The visual hull sampling process attempts to intersect an object's projection cone with the cones of minimal subsets of other similar objects among those pictured from certain vantage points. We show that our method is able to produce convincing per-object 3D reconstructions and to accurately estimate cameras viewpoints on one of the most challenging existing object-category detection datasets, PASCAL VOC. We hope that our results will re-stimulate interest on joint object recognition and 3D reconstruction from a single image.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑