# Deep Models with Fusion Strategies for MVP Point Cloud Registration

arXiv: https://arxiv.org/abs/2110.09129 · HTML: https://mlsanity.com/paper/2110.09129/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://mlsanity.com/paper/2008.09088/) (2020)
- [Correspondence Matrices are Underrated](https://mlsanity.com/paper/2010.16085/) (2020)

## Abstract (arXiv)

The main goal of point cloud registration in Multi-View Partial (MVP) Challenge 2021 is to estimate a rigid transformation to align a point cloud pair. The pairs in this competition have the characteristics of low overlap, non-uniform density, unrestricted rotations and ambiguity, which pose a huge challenge to the registration task. In this report, we introduce our solution to the registration task, which fuses two deep learning models: ROPNet and PREDATOR, with customized ensemble strategies. Finally, we achieved the second place in the registration track with 2.96546, 0.02632 and 0.07808 under the the metrics of RotError, TransError and MSE, respectively.