NeRD:神经三维反射对称性检测器
NeRD: Neural 3D Reflection Symmetry Detector
摘要:
最近的进展表明,对称性,大多数物体表现出的结构先验,可以支持各种单视图3D理解任务。然而,从图像中检测3D对称性仍然是一项具有挑战性的任务。以前的作品要么假设对称性是给定的,要么用基于几何的方法检测对称性。在本文中,我们提出了NeRD,一个神经3D反射对称检测器,它结合了基于学习的识别和基于几何的重建的强度,以准确地恢复对象的镜面的法线方向。具体来说,我们首先枚举的对称平面与粗到细的策略,然后找到最好的,通过建立3D成本卷检查图像内的像素对应的对称性。我们的实验表明,用我们的方法检测到的对称平面比直接CNN回归在合成和真实世界数据集上的平面更准确。我们还证明了检测到的对称性可以用于提高下游任务的性能,如姿势估计和深度图回归。本文的代码已在https://github.com/zhou13/nerd上公布。
英文摘要:
Recent advances have shown that symmetry, a structural prior that most objects exhibit, can support a variety of single-view 3D understanding tasks. However, detecting 3D symmetry from an image remains a challenging task. Previous works either assume that the symmetry is given or detect the symmetry with a heuristic-based method. In this paper, we present NeRD, a Neural 3D Reflection Symmetry Detector, which combines the strength of learning-based recognition and geometry-based reconstruction to accurately recover the normal direction of objects' mirror planes. Specifically, we first enumerate the symmetry planes with a coarse-to-fine strategy and then find the best ones by building 3D cost volumes to examine the intra-image pixel correspondence from the symmetry. Our experiments show that the symmetry planes detected with our method are significantly more accurate than the planes from direct CNN regression on both synthetic and real-world datasets. We also demonstrate that the detected symmetry can be used to improve the performance of downstream tasks such as pose estimation and depth map regression. The code of this paper has been made public at https://github.com/zhou13/nerd.
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。