Search papers, labs, and topics across Lattice.
This paper introduces TrackDeform3D, a novel framework for markerless and autonomous 3D keypoint tracking of deformable objects using RGB-D cameras. It leverages motion consistency constraints to ensure temporally smooth and geometrically coherent tracking, addressing the limitations of existing methods in handling complex deformations. The framework is used to create a large-scale dataset of 6 deformable objects with 110 minutes of trajectory data, demonstrating improved geometric and tracking accuracy compared to state-of-the-art methods.
Forget labor-intensive annotation or expensive motion capture: TrackDeform3D offers an affordable, autonomous RGB-D framework for high-quality 3D tracking and dataset collection of deformable objects.
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.
