TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects

TL;DR

This paper introduces TrackDeform3D, an autonomous RGB-D based system for collecting large-scale 3D deformable object datasets with accurate keypoint tracking, addressing the scarcity of such data for research.

Contribution

It presents a novel, affordable framework for autonomous 3D data collection of deformable objects, improving keypoint tracking accuracy and enabling large-scale dataset creation.

Findings

TrackDeform3D outperforms state-of-the-art methods in accuracy.

The framework successfully collects 110 minutes of high-quality deformable object data.

The dataset includes diverse object categories and trajectories.

Abstract

Structured 3D representations such as keypoints and meshes offer compact, expressive descriptions of deformable objects, jointly capturing geometric and topological information useful for downstream tasks such as dynamics modeling and motion planning. However, robustly extracting such representations remains challenging, as current perception methods struggle to handle complex deformations. Moreover, large-scale 3D data collection remains a bottleneck: existing approaches either require prohibitive data collection efforts, such as labor-intensive annotation or expensive motion capture setups, or rely on simplifying assumptions that break down in unstructured environments. As a result, large-scale 3D datasets and benchmarks for deformable objects remain scarce. To address these challenges, this paper presents an affordable and autonomous framework for collecting 3D datasets of deformable objects using only RGB-D cameras. The proposed method identifies 3D keypoints and robustly tracks their trajectories, incorporating motion consistency constraints to produce temporally smooth and geometrically coherent data. TrackDeform3D is evaluated against several state-of-the-art tracking methods across diverse object categories and demonstrates consistent improvements in both geometric and tracking accuracy. Using this framework, this paper presents a high-quality, large-scale dataset consisting of 6 deformable objects, totaling 110 minutes of trajectory data.