# CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

arXiv: https://arxiv.org/abs/2012.15638 · HTML: https://mlsanity.com/paper/2012.15638/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 30 of 47)

- [A Survey of Non-Rigid 3D Registration](https://mlsanity.com/paper/2203.07858/) (2022)
- [Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features](https://mlsanity.com/paper/2311.17024/) (2023)
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2202.13589/) (2022)
- [CorrI2P: Deep Image-to-Point Cloud Registration via Dense Correspondence](https://mlsanity.com/paper/2207.05483/) (2022)
- [SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow](https://mlsanity.com/paper/2211.14020/) (2022)
- [Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation](https://mlsanity.com/paper/2402.18920/) (2024)
- [OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds](https://mlsanity.com/paper/2210.04458/) (2022)
- [Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching](https://mlsanity.com/paper/2303.10971/) (2023)
- [Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction](https://mlsanity.com/paper/2211.10278/) (2022)
- [NICP: Neural ICP for 3D Human Registration at Scale](https://mlsanity.com/paper/2312.14024/) (2023)
- [3D Implicit Transporter for Temporally Consistent Keypoint Discovery](https://mlsanity.com/paper/2309.05098/) (2023)
- [A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching](https://mlsanity.com/paper/2204.12805/) (2022)
- [SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence](https://mlsanity.com/paper/2304.05395/) (2023)
- [Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud](https://mlsanity.com/paper/2305.14486/) (2023)
- [Denoising Functional Maps: Diffusion Models for Shape Correspondence](https://mlsanity.com/paper/2503.01845/) (2025)
- [Implicit field supervision for robust non-rigid shape matching](https://mlsanity.com/paper/2203.07694/) (2022)
- [Non-Rigid Shape Registration via Deep Functional Maps Prior](https://mlsanity.com/paper/2311.04494/) (2023)
- [Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation](https://mlsanity.com/paper/2405.16849/) (2024)
- [DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features](https://mlsanity.com/paper/2408.08568/) (2024)
- [Neural Intrinsic Embedding for Non-rigid Point Cloud Matching](https://mlsanity.com/paper/2303.01038/) (2023)
- [Reduced Representation of Deformation Fields for Effective Non-rigid Shape Matching](https://mlsanity.com/paper/2211.14604/) (2022)
- [DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction](https://mlsanity.com/paper/2403.11586/) (2024)
- [PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation](https://mlsanity.com/paper/2212.14197/) (2022)
- [Dynamic 3D Point Cloud Sequences as 2D Videos](https://mlsanity.com/paper/2403.01129/) (2024)
- [Unsupervised Template-assisted Point Cloud Shape Correspondence Network](https://mlsanity.com/paper/2403.16412/) (2024)
- [Towards 3D Scene Understanding by Referring Synthetic Models](https://mlsanity.com/paper/2203.10546/) (2022)
- [SAS: Segment Any 3D Scene with Integrated 2D Priors](https://mlsanity.com/paper/2503.08512/) (2025)
- [Diffusion Masked Pretraining for Dynamic Point Cloud](https://mlsanity.com/paper/2605.03639/) (2026)
- [End-to-end Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration](https://mlsanity.com/paper/2110.15250/) (2021)
- [Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images](https://mlsanity.com/paper/2111.04237/) (2021)

## Abstract (arXiv)

Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to drive the learning of dense correspondence between 3D shapes by means of deformation-like reconstruction to overcome the need for annotated data. Specifically, CorrNet3D consists of a deep feature embedding module and two novel modules called correspondence indicator and symmetric deformer. Feeding a pair of raw point clouds, our model first learns the pointwise features and passes them into the indicator to generate a learnable correspondence matrix used to permute the input pair. The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence. The extensive experiments on both synthetic and real-world datasets of rigid and non-rigid 3D shapes show our CorrNet3D outperforms state-of-the-art methods to a large extent, including those taking meshes as input. CorrNet3D is a flexible framework in that it can be easily adapted to supervised learning if annotated data are available. The source code and pre-trained model will be available at https://github.com/ZENGYIMING-EAMON/CorrNet3D.git.