# Cascading Feature Extraction for Fast Point Cloud Registration

arXiv: https://arxiv.org/abs/2110.12204 · HTML: https://mlsanity.com/paper/2110.12204/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 23 Oct 2021.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Learning Latent Permutations with Gumbel-Sinkhorn Networks](https://mlsanity.com/paper/1802.08665/) (2018)
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://mlsanity.com/paper/2005.01014/) (2020)
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://mlsanity.com/paper/2103.04256/) (2021)

## Built on by (most cited first, 1 of 1)

- [Unsupervised Point Cloud Registration with Self-Distillation](https://mlsanity.com/paper/2409.07558/) (2024)

## Abstract (arXiv)

We propose a method for speeding up a 3D point cloud registration through a cascading feature extraction. The current approach with the highest accuracy is realized by iteratively executing feature extraction and registration using deep features. However, iterative feature extraction takes time. Our proposed method significantly reduces the computational cost using cascading shallow layers. Our idea is to omit redundant computations that do not always contribute to the final accuracy. The proposed approach is approximately three times faster than the existing methods without a loss of accuracy.