TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation

TL;DR

TransNet introduces a novel two-stage method for category-level pose estimation of transparent objects, overcoming visual and depth sensing challenges, and demonstrates improved accuracy in robotic manipulation tasks.

Contribution

The paper presents TransNet, a new approach for transparent object pose estimation that leverages localized depth completion and surface normal estimation, advancing beyond existing methods.

Findings

TransNet outperforms state-of-the-art category-level pose estimation methods on transparent objects.

TransNet enables effective robotic pick-and-place and pouring with transparent objects.

The approach improves perception accuracy despite transparency-related sensing challenges.

Abstract

Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain transparent surfaces with little specular reflection or refraction, like glass doors, difficult to perceive. A second challenge is that depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent surfaces due to their unique reflective properties. Stemming from these challenges, we observe that transparent object instances within the same category, such as cups, look more similar to each other than to ordinary opaque objects of that same category. Given this observation, the present paper explores the possibility of category-level transparent object pose estimation rather than instance-level pose estimation. We propose \textit{\textbf{TransNet}}, a two-stage pipeline that estimates category-level transparent object pose using localized depth completion and surface normal estimation. TransNet is evaluated in terms of pose estimation accuracy on a large-scale transparent object dataset and compared to a state-of-the-art category-level pose estimation approach. Results from this comparison demonstrate that TransNet achieves improved pose estimation accuracy on transparent objects. Moreover, we use TransNet to build an autonomous transparent object manipulation system for robotic pick-and-place and pouring tasks.