# Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction

arXiv: https://arxiv.org/abs/2203.10212 · HTML: https://mlsanity.com/paper/2203.10212/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [Neural Cages for Detail-Preserving 3D Deformations](https://mlsanity.com/paper/1912.06395/) (2019)
- [Learning elementary structures for 3D shape generation and matching](https://mlsanity.com/paper/1908.04725/) (2019)
- [USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds](https://mlsanity.com/paper/1904.00229/) (2019)
- [C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion](https://mlsanity.com/paper/1909.02533/) (2019)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://mlsanity.com/paper/2104.11224/) (2021)
- [Unsupervised Learning of Intrinsic Structural Representation Points](https://mlsanity.com/paper/2003.01661/) (2020)
- [Skeleton Merger: an Unsupervised Aligned Keypoint Detector](https://mlsanity.com/paper/2103.10814/) (2021)
- [Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets](https://mlsanity.com/paper/2003.07619/) (2020)

## Built on by (most cited first, 5 of 5)

- [SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data](https://mlsanity.com/paper/2308.05410/) (2023)
- [Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features](https://mlsanity.com/paper/2410.02237/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [SelfGeo: Self-supervised and Geodesic-consistent Estimation of Keypoints on Deformable Shapes](https://mlsanity.com/paper/2408.02291/) (2024)
- [PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation](https://mlsanity.com/paper/2508.05976/) (2025)

## Abstract (arXiv)

Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic information, especially when the objects are represented by unordered 3D point clouds. Existing unsupervised methods tend to generate category-level keypoints in implicit manners, making it difficult to extract high-level information, such as semantic labels and topology. From a novel mutual reconstruction perspective, we present an unsupervised method to generate consistent semantic keypoints from point clouds explicitly. To achieve this, the proposed model predicts keypoints that not only reconstruct the object itself but also reconstruct other instances in the same category. To the best of our knowledge, the proposed method is the first to mine 3D semantic consistent keypoints from a mutual reconstruction view. Experiments under various evaluation metrics as well as comparisons with the state-of-the-arts demonstrate the efficacy of our new solution to mining semantic consistent keypoints with mutual reconstruction.