# Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration

arXiv: https://arxiv.org/abs/2006.04523 · HTML: https://mlsanity.com/paper/2006.04523/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2020.

## Built on by (most cited first, 9 of 9)

- [Accurate Point Cloud Registration with Robust Optimal Transport](https://mlsanity.com/paper/2111.00648/) (2021)
- [Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey](https://mlsanity.com/paper/2305.05080/) (2023)
- [PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds](https://mlsanity.com/paper/2110.01269/) (2021)
- [COTReg:Coupled Optimal Transport based Point Cloud Registration](https://mlsanity.com/paper/2112.14381/) (2021)
- [PCRDiffusion: Diffusion Probabilistic Models for Point Cloud Registration](https://mlsanity.com/paper/2312.06063/) (2023)
- [Deep Confidence Guided Distance for 3D Partial Shape Registration](https://mlsanity.com/paper/2201.11379/) (2022)
- [Partial Transport for Point-Cloud Registration](https://mlsanity.com/paper/2309.15787/) (2023)
- [SDFReg: Learning Signed Distance Functions for Point Cloud Registration](https://mlsanity.com/paper/2304.08929/) (2023)
- [COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation](https://mlsanity.com/paper/2603.00493/) (2026)

## Abstract (arXiv)

While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results. In this context, however, only PRNet can handle the partial-to-partial registration scenario. Unfortunately, this is achieved at the cost of relying on an iterative procedure, with a complex network architecture. Here, we show that learning-based partial-to-partial registration can be achieved in a one-shot manner, jointly reducing network complexity and increasing registration accuracy. To this end, we propose an Optimal Transport layer able to account for occluded points thanks to the use of outlier bins. The resulting OPRNet framework outperforms the state of the art on standard benchmarks, demonstrating better robustness and generalization ability than existing techniques.