arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.01929cs.CVcs.LGcs.RO
收藏

CenterSnap:单次拍摄多对象3D形状重建和分类6D姿态和大小估计

CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation

Georgia Institute of Technology(佐治亚理工学院);Toyota Research Institute(丰田研究院)

Muhammad Zubair Irshad, Thomas Kollar, Michael Laskey, Kevin Stone, Zsolt Kira

摘要:

本文研究了从单视图RGB-D观测同时进行多目标3D重建、6D姿态和尺寸估计的复杂任务。与实例级姿态估计相比,我们专注于一个更具挑战性的问题,其中CAD模型在推理时不可用。现有的方法主要遵循一个复杂的多阶段流水线,首先定位和检测图像中的每个对象实例,然后回归到它们的3D网格或6D姿态。这些方法在复杂的多对象场景中存在高计算成本和低性能,其中可能存在遮挡。因此,我们提出了一个简单的一阶段的方法来预测的3D形状和估计的6D姿态和大小联合在一个无边界框的方式。特别是,我们的方法将对象实例视为空间中心,其中每个中心表示对象的完整形状及其6D姿态和大小。通过这种逐像素表示,我们的方法可以实时(40 FPS)重建多个新对象实例,并在单次向前传递中预测它们的6D姿态和大小。通过大量的实验,我们证明了我们的方法在多对象ShapeNet和NOCS数据集上分别显著优于所有形状完成和分类6D姿态和大小估计基线,对于新的真实世界对象实例,6D姿态的mAP绝对提高了12.6%。

英文摘要:

This paper studies the complex task of simultaneous multi-object 3D reconstruction, 6D pose and size estimation from a single-view RGB-D observation. In contrast to instance-level pose estimation, we focus on a more challenging problem where CAD models are not available at inference time. Existing approaches mainly follow a complex multi-stage pipeline which first localizes and detects each object instance in the image and then regresses to either their 3D meshes or 6D poses. These approaches suffer from high-computational cost and low performance in complex multi-object scenarios, where occlusions can be present. Hence, we present a simple one-stage approach to predict both the 3D shape and estimate the 6D pose and size jointly in a bounding-box free manner. In particular, our method treats object instances as spatial centers where each center denotes the complete shape of an object along with its 6D pose and size. Through this per-pixel representation, our approach can reconstruct in real-time (40 FPS) multiple novel object instances and predict their 6D pose and sizes in a single-forward pass. Through extensive experiments, we demonstrate that our approach significantly outperforms all shape completion and categorical 6D pose and size estimation baselines on multi-object ShapeNet and NOCS datasets respectively with a 12.6% absolute improvement in mAP for 6D pose for novel real-world object instances.

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。

↑