# MATTER: Multiscale Attention for Registration Error Regression

arXiv: https://arxiv.org/abs/2509.12924 · HTML: https://mlsanity.com/paper/2509.12924/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 22 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAM](https://mlsanity.com/paper/2311.00928/) (2023)
- [Uncertainty Quantification Metrics for Deep Regression](https://mlsanity.com/paper/2405.04278/) (2024)
- [CorAl -- Are the point clouds Correctly Aligned?](https://mlsanity.com/paper/2109.09820/) (2021)
- [FACT: Multinomial Misalignment Classification for Point Cloud Registration](https://mlsanity.com/paper/2504.06627/) (2025)

## Abstract (arXiv)

Point cloud registration (PCR) is crucial for many downstream tasks, such as simultaneous localization and mapping (SLAM) and object tracking. This makes detecting and quantifying registration misalignment, i.e., PCR quality validation, an important task. All existing methods treat validation as a classification task, aiming to assign the PCR quality to a few classes. In this work, we instead use regression for PCR validation, allowing for a more fine-grained quantification of the registration quality. We also extend previously used misalignment-related features by using multiscale extraction and attention-based aggregation. This leads to accurate and robust registration error estimation on diverse datasets, especially for point clouds with heterogeneous spatial densities. Furthermore, when used to guide a mapping downstream task, our method significantly improves the mapping quality for a given amount of re-registered frames, compared to the state-of-the-art classification-based method.