Skeleton Merger: An Unsupervised Aligned Keypoint Detector

Abstract

Detecting aligned 3D keypoints is essential under many scenarios such as object tracking, shape retrieval and robotics. However, it is generally hard to prepare a high-quality dataset for all types of objects due to the ambiguity of keypoint itself. Meanwhile, current unsupervised detectors are unable to generate aligned keypoints with good coverage. In this paper, we propose an unsupervised aligned keypoint detector, Skeleton Merger, which utilizes skeletons to reconstruct objects. It is based on an Autoencoder architecture. The encoder proposes keypoints and predicts activation strengths of edges between keypoints. The decoder performs uniform sampling on the skeleton and refines it into small point clouds with pointwise offsets. Then the activation strengths are applied and the sub-clouds are merged. Composite Chamfer Distance (CCD) is proposed as a distance between the input point cloud and the reconstruction composed of sub-clouds masked by activation strengths. We demonstrate tha

Stats

• citations38
• S2 citations—
• github stars74
• HF likes0
• heat score15.68
• arxiv keyshi2021skeleton

Related papers

• KP-RED: Exploiting Semantic Keypoints For Joint 3D Shape Retrieval And Deformation (2024)8.35
• Improving The Matching Of Deformable Objects By Learning To Detect Keypoints (2023)7.74
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40
• Shapematcher: Self-supervised Joint Shape Canonicalization, Segmentation, Retrieval And Deformation (2023)6.77
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76
• Ur2kid: Unifying Retrieval, Keypoint Detection, And Keypoint Description Without Local Correspondence Supervision (2020)0.00
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Enhancing Deformable Local Features By Jointly Learning To Detect And Describe Keypoints (2023)9.59