FDCT: Fast Depth Completion for Transparent Objects

TL;DR

FDCT is a fast and accurate depth completion method specifically designed for transparent objects, enabling real-time applications in robotics with improved pose estimation capabilities.

Contribution

The paper introduces FDCT, a novel framework that efficiently completes depth maps for transparent objects using a new fusion architecture and loss function, outperforming existing methods in speed and accuracy.

Findings

FDCT achieves 70 FPS in depth completion.

FDCT outperforms state-of-the-art methods in accuracy.

FDCT enhances object pose estimation in robotic grasping.

Abstract

Depth completion is crucial for many robotic tasks such as autonomous driving, 3-D reconstruction, and manipulation. Despite the significant progress, existing methods remain computationally intensive and often fail to meet the real-time requirements of low-power robotic platforms. Additionally, most methods are designed for opaque objects and struggle with transparent objects due to the special properties of reflection and refraction. To address these challenges, we propose a Fast Depth Completion framework for Transparent objects (FDCT), which also benefits downstream tasks like object pose estimation. To leverage local information and avoid overfitting issues when integrating it with global information, we design a new fusion branch and shortcuts to exploit low-level features and a loss function to suppress overfitting. This results in an accurate and user-friendly depth rectification framework which can recover dense depth estimation from RGB-D images alone. Extensive experiments demonstrate that FDCT can run about 70 FPS with a higher accuracy than the state-of-the-art methods. We also demonstrate that FDCT can improve pose estimation in object grasping tasks. The source code is available at https://github.com/Nonmy/FDCT