DLODepth: Real-time Depth Recovery for 3D Reflective Deformable Linear Object

Li Huang, Tong Yang, Xiang Tian, Rongxin Jiang, Yaowu Chen

Attend In Person: Yes

Keywords: DLO Perception;Depth Recovery;Sensor Fusion;

TL;DR: An end-to-end monocular framework achieves state-of-the-art 3D reconstruction of Deformable Linear Objects from highly noisy inputs.

Abstract:

An end-to-end monocular 3D recovery framework for Deformable Linear Object (DLO) is proposed in this paper.
The fragmented and unreliable 3D point clouds caused by the thin profile and reflective surfaces of DLOs have been a critical challenge in 3D DLO perception.
Conventional algorithms circumvent these issues by relying on simplified background environments or expensive multi-sensor systems, yet such constraints severely limit their practical downstream applications.
This paper proposes a mixed body of multiple branches, including RGB segmentation, relative depth estimation, relative-to-metric scaling transformation, and a recovery fusion module.
Our framework achieves state-of-the-art performance in recovering DLO from highly noisy inputs, recovering 93.8\% (median) of the target point cloud within a 5cm error band, with a mean distance error of 4.3cm.
An open-sourcing implementation of the proposed algorithm, a GUI-based data collection tool, and a ready-to-use dataset have also been provided for the benefit of the community.

Submission Number: 18