arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08797cs.CV
收藏

MonoGRNet:一个通用的单目三维目标检测框架

MonoGRNet: A General Framework for Monocular 3D Object Detection

Massachusetts Institute of Technology(麻省理工学院);Microsoft Research Asia(微软亚洲研究院)

Zengyi Qin, Jinglu Wang, Yan Lu

摘要:

在真实3D空间中检测和定位物体在场景理解中起着至关重要的作用,由于图像投影期间的几何信息丢失,仅给定单目图像是特别具有挑战性的。我们提出MonoGRNet的非模态三维目标检测从单目图像通过几何推理在观察到的二维投影和未观察到的深度维度。MonoGRNet将单目3D目标检测任务分解为四个子任务,包括2D目标检测、实例级深度估计、投影3D中心估计和局部角点回归。任务分解显著地促进了单目3D目标检测,允许在单个前向通路中有效地预测目标3D边界框,而不使用对象提议、后处理或由先前方法利用的计算上昂贵的像素级深度估计。此外,MonoGRNet灵活地适应完全和弱监督学习,这提高了我们的框架在不同环境中的可行性。实验在KITTI、Cityscapes和MS COCO数据集上进行。结果表明,我们的框架在各种情况下的良好表现。

英文摘要:

Detecting and localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a monocular image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object detection from a monocular image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet decomposes the monocular 3D object detection task into four sub-tasks including 2D object detection, instance-level depth estimation, projected 3D center estimation and local corner regression. The task decomposition significantly facilitates the monocular 3D object detection, allowing the target 3D bounding boxes to be efficiently predicted in a single forward pass, without using object proposals, post-processing or the computationally expensive pixel-level depth estimation utilized by previous methods. In addition, MonoGRNet flexibly adapts to both fully and weakly supervised learning, which improves the feasibility of our framework in diverse settings. Experiments are conducted on KITTI, Cityscapes and MS COCO datasets. Results demonstrate the promising performance of our framework in various scenarios.

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。

↑