Reconstructing transparent objects using affordable RGB-D cameras is a
persistent challenge in robotic perception due to inconsistent appearances
across views in the RGB domain and inaccurate depth readings in each
single-view. We introduce a two-stage pipeline for reconstructing transparent
objects tailored for mobile platforms. In the first stage, off-the-shelf
monocular object segmentation and depth completion networks are leveraged to
predict the depth of transparent objects, furnishing single-view shape prior.
Subsequently, we propose Epipolar-guided Optical Flow (EOF) to fuse several
single-view shape priors from the first stage to a cross-view consistent 3D
reconstruction given camera poses estimated from opaque part of the scene. Our
key innovation lies in EOF which employs boundary-sensitive sampling and
epipolar-line constraints into optical flow to accurately establish 2D
correspondences across multiple views on transparent objects. Quantitative
evaluations demonstrate that our pipeline significantly outperforms baseline
methods in 3D reconstruction quality, paving the way for more adept robotic
perception and interaction with transparent objects.

使用廉价的 RGB-D 相机对透明物体进行重建是机器人感知中的持久挑战，由于 RGB 领域中视图不一致以及单视图中不准确的深度读数。我们提出了一个专为移动平台量身定制的透明物体重建两阶段流程：在第一阶段，利用现成的单目物体分割和深度补全网络来预测透明物体的深度，提供单视图形状先验信息；随后，我们提出了基于极线引导的光流（Epipolar-guided Optical Flow），将第一阶段的多个单视图形状先验信息融合到一个在摄像机姿态中估计的跨视图一致的 3D 重建中。我们的创新在于 Epipolar-guided Optical Flow，它在光流中引入了边界敏感采样和极线约束，以在透明物体上准确建立 2D 对应关系。定量评估表明，我们的流程在 3D 重建质量上明显优于基准方法，为更熟练地感知和与透明物体交互铺平了道路。