Coe: Deep Coupled Embedding For Non-rigid Point Cloud Correspondences

Abstract

The interest in matching non-rigidly deformed shapes represented as raw point clouds is rising due to the proliferation of low-cost 3D sensors. Yet, the task is challenging since point clouds are irregular and there is a lack of intrinsic shape information. We propose to tackle these challenges by learning a new shape representation -- a per-point high dimensional embedding, in an embedding space where semantically similar points share similar embeddings. The learned embedding has multiple beneficial properties: it is aware of the underlying shape geometry and is robust to shape deformations and various shape artefacts, such as noise and partiality. Consequently, this embedding can be directly employed to retrieve high-quality dense correspondences through a simple nearest neighbor search in the embedding space. Extensive experiments demonstrate new state-of-the-art results and robustness in numerous challenging non-rigid shape matching benchmarks and show its great potential in other

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzeng2024coe

Related papers

• Parts2words: Learning Joint Embedding Of Point Clouds And Texts By Bidirectional Matching Between Parts And Words (2021)9.96
• Improving The Matching Of Deformable Objects By Learning To Detect Keypoints (2023)7.74
• Bayesian Inference Of Bijective Non-rigid Shape Correspondence (2016)0.00
• KP-RED: Exploiting Semantic Keypoints For Joint 3D Shape Retrieval And Deformation (2024)8.35
• Joint Learning Of 3D Shape Retrieval And Deformation (2021)11.08
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• REGTR: End-to-end Point Cloud Correspondences With Transformers (2022)22.67
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40