# DeepBBS: Deep Best Buddies for Point Cloud Registration

arXiv: https://arxiv.org/abs/2110.03016 · HTML: https://mlsanity.com/paper/2110.03016/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 51 references that are in the map.
- First posted on arXiv 6 Oct 2021.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [TEASER: Fast and Certifiable Point Cloud Registration](https://mlsanity.com/paper/2001.07715/) (2020)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](https://mlsanity.com/paper/1910.12240/) (2019)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration](https://mlsanity.com/paper/1905.04153/) (2019)
- [PCRNet: Point Cloud Registration Network using PointNet Encoding](https://mlsanity.com/paper/1908.07906/) (2019)
- [FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization](https://mlsanity.com/paper/1811.10136/) (2018)
- [PointGMM: a Neural GMM Network for Point Clouds](https://mlsanity.com/paper/2003.13326/) (2020)
- [MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment](https://mlsanity.com/paper/2002.12623/) (2020)
- [AA-ICP: Iterative Closest Point with Anderson Acceleration](https://mlsanity.com/paper/1709.05479/) (2017)
- [Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors](https://mlsanity.com/paper/1609.01571/) (2016)
- [Best Buddies Registration for Point Clouds](https://mlsanity.com/paper/2010.01912/) (2020)

## Built on by (most cited first, 2 of 2)

- [VF-NeRF: Viewshed Fields for Rigid NeRF Registration](https://mlsanity.com/paper/2404.03349/) (2024)
- [epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition](https://mlsanity.com/paper/2403.06661/) (2024)

## Abstract (arXiv)

Recently, several deep learning approaches have been proposed for point cloud registration. These methods train a network to generate a representation that helps finding matching points in two 3D point clouds. Finding good matches allows them to calculate the transformation between the point clouds accurately. Two challenges of these techniques are dealing with occlusions and generalizing to objects of classes unseen during training. This work proposes DeepBBS, a novel method for learning a representation that takes into account the best buddy distance between points during training. Best Buddies (i.e., mutual nearest neighbors) are pairs of points nearest to each other. The Best Buddies criterion is a strong indication for correct matches that, in turn, leads to accurate registration. Our experiments show improved performance compared to previous methods. In particular, our learned representation leads to an accurate registration for partial shapes and in unseen categories.