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

TL;DR

This paper introduces a large-scale real-world dataset for transparent object depth completion and proposes an effective end-to-end network, significantly improving robotic grasping of transparent objects in cluttered scenes.

Contribution

The work provides the first large-scale real-world dataset for transparent object depth completion and develops a robust, efficient depth completion network for robotic grasping applications.

Findings

The dataset contains 57,715 RGB-D images from 130 scenes.

The proposed network outperforms previous methods in accuracy and efficiency.

Robotic experiments demonstrate successful grasping of transparent objects.

Abstract

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 over previous works, and it is able to process images of high resolutions under limited hardware resources. Real robot experiments show that our method can also be applied to novel transparent object grasping robustly. The full dataset and our method are publicly available at www.graspnet.net/transcg