Can I read TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline on EtoBox?

TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline by Fang, Hongjie; Fang, Hao-Shu; Xu, Sheng; Lu, Cewu is a scholarly article available to read on EtoBox.

What is TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline about?

Transparent objects are common in our daily life and frequently handled in the automated production line. Robust vision-based robotic grasping and manipulation for these objects would be beneficial for automation. However, the majority of current grasping algorithms would fail in this case since they heavily rely on the depth image, while ordinary depth sensors usually fail to produce accurate depth information for transparent objects owing to the reflection and refraction of light. In this work, we address this issue by contributing a large-scale real-world dataset for transparent object depth completion, which contains 57,715 RGB-D images from 130 different scenes. Our dataset is the first large-scale, real-world dataset that provides ground truth depth, surface normals, transparent masks in diverse and cluttered scenes. Cross-domain experiments show that our dataset is more general and can enable better generalization ability for models. Moreover, we propose an end-to-end depth completion network, which takes the RGB image and the inaccurate depth map as inputs and outputs a refined depth map. Experiments demonstrate superior efficacy, efficiency and robustness of our method ove

Author

Fang, Hongjie; Fang, Hao-Shu; Xu, Sheng; Lu, Cewu

Published

2022

Language

EN