# R-SLPR: Region-based Small-to-Large Point-cloud Registration with Contrastive Learning

arXiv: https://arxiv.org/abs/2607.26583 · HTML: https://mlsanity.com/paper/2607.26583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 29 Jul 2026.

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

- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [Deep Weighted Consensus: Dense correspondence confidence maps for 3D shape registration](https://mlsanity.com/paper/2105.02714/) (2021)

## Abstract (arXiv)

Point-cloud (PC) registration is fundamental to three-dimensional (3D) perception in robotic systems. However, classic registration algorithms falter when aligning a source PC containing limited, incomplete, or ambiguous geometric cues against a reference. This challenge of registering a small, partial PC to a significantly larger global reference is pervasive in real-world deployment yet remains insufficiently addressed by existing learning-based approaches, which typically assume comparable scales and significant overlap. To bridge this gap, we propose the Region-based Small-to-Large Point-cloud Registra- tion framework (R-SLPR), a novel three-stage architecture that fundamentally reformulates the scale-mismatched registration problem into a sequence of region proposal, regional matching, and iterative refinement. Unlike conventional methods that fail to localize specific regions, R-SLPR explicitly identifies candidate regions prior to estimating rigid transformations, ensuring robust alignment even under severe scale mismatch. The framework introduces a Fibonacci Grid Segmentation method coupled with a contrastive learning objective to effectively generate and match local geometric patches. Building on this, a novel Cascade Anchor Selection and Refinement algorithm iteratively aligns the source with the target region to maximize precision. Extensive evaluation on ModelNet40 demonstrates that R-SLPR establishes a new state-of-the-art accuracy standard, outperforming prior approaches and significantly reducing position and rotation Mean Absolute Error (MAE) to 0.009 and 1.104, respectively.