Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects

TL;DR

This paper introduces TranspareNet, a novel joint point cloud and depth completion method designed to improve perception of transparent objects in cluttered scenes, supported by a new large-scale dataset and automated data collection workflow.

Contribution

The paper presents TranspareNet, a new depth completion approach for transparent objects, and a scalable automated dataset creation process, addressing limitations of existing transparent object datasets.

Findings

TranspareNet outperforms state-of-the-art depth completion methods.

The method effectively handles cluttered scenes with transparent objects.

The new dataset TODD enables robust training and evaluation.

Abstract

The basis of many object manipulation algorithms is RGB-D input. Yet, commodity RGB-D sensors can only provide distorted depth maps for a wide range of transparent objects due light refraction and absorption. To tackle the perception challenges posed by transparent objects, we propose TranspareNet, a joint point cloud and depth completion method, with the ability to complete the depth of transparent objects in cluttered and complex scenes, even with partially filled fluid contents within the vessels. To address the shortcomings of existing transparent object data collection schemes in literature, we also propose an automated dataset creation workflow that consists of robot-controlled image collection and vision-based automatic annotation. Through this automated workflow, we created Toronto Transparent Objects Depth Dataset (TODD), which consists of nearly 15000 RGB-D images. Our experimental evaluation demonstrates that TranspareNet outperforms existing state-of-the-art depth completion methods on multiple datasets, including ClearGrasp, and that it also handles cluttered scenes when trained on TODD. Code and dataset will be released at https://www.pair.toronto.edu/TranspareNet/