# MODNet: Multi-offset Point Cloud Denoising Network Customized for Multi-scale Patches

arXiv: https://arxiv.org/abs/2208.14160 · HTML: https://mlsanity.com/paper/2208.14160/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 30 Aug 2022.

## Builds on (most cited first, 18 of 18)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds](https://mlsanity.com/paper/1901.01060/) (2019)
- [PCPNET: Learning Local Shape Properties from Raw Point Clouds](https://mlsanity.com/paper/1710.04954/) (2017)
- [EC-Net: an Edge-aware Point set Consolidation Network](https://mlsanity.com/paper/1807.06010/) (2018)
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://mlsanity.com/paper/2005.13888/) (2020)
- [Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning](https://mlsanity.com/paper/1904.07615/) (2019)
- [Pointfilter: Point Cloud Filtering via Encoder-Decoder Modeling](https://mlsanity.com/paper/2002.05968/) (2020)
- [3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model](https://mlsanity.com/paper/1803.07252/) (2018)
- [Learning Graph-Convolutional Representations for Point Cloud Denoising](https://mlsanity.com/paper/2007.02578/) (2020)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [Feature Graph Learning for 3D Point Cloud Denoising](https://mlsanity.com/paper/1907.09138/) (2019)
- [Graph Signal Processing for Geometric Data and Beyond: Theory and Applications](https://mlsanity.com/paper/2008.01918/) (2020)
- [Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance](https://mlsanity.com/paper/2003.08355/) (2020)
- [Graph-based denoising for time-varying point clouds](https://mlsanity.com/paper/1511.04902/) (2015)

## Built on by (most cited first, 5 of 5)

- [Deep Learning for 3D Point Cloud Enhancement: A Survey](https://mlsanity.com/paper/2411.00857/) (2024)
- [Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model](https://mlsanity.com/paper/2509.14560/) (2025)
- [LBF:Learnable Bilateral Filter For Point Cloud Denoising](https://mlsanity.com/paper/2210.15950/) (2022)
- [A Survey of Deep Learning-based Point Cloud Denoising](https://mlsanity.com/paper/2508.17011/) (2025)
- [UGD: An Unsupervised Geometric Distance for Evaluating Real-world Noisy Point Cloud Denoising](https://mlsanity.com/paper/2604.16976/) (2026)

## Abstract (arXiv)

The intricacy of 3D surfaces often results cutting-edge point cloud denoising (PCD) models in surface degradation including remnant noise, wrongly-removed geometric details. Although using multi-scale patches to encode the geometry of a point has become the common wisdom in PCD, we find that simple aggregation of extracted multi-scale features can not adaptively utilize the appropriate scale information according to the geometric information around noisy points. It leads to surface degradation, especially for points close to edges and points on complex curved surfaces. We raise an intriguing question -- if employing multi-scale geometric perception information to guide the network to utilize multi-scale information, can eliminate the severe surface degradation problem? To answer it, we propose a Multi-offset Denoising Network (MODNet) customized for multi-scale patches. First, we extract the low-level feature of three scales patches by patch feature encoders. Second, a multi-scale perception module is designed to embed multi-scale geometric information for each scale feature and regress multi-scale weights to guide a multi-offset denoising displacement. Third, a multi-offset decoder regresses three scale offsets, which are guided by the multi-scale weights to predict the final displacement by weighting them adaptively. Experiments demonstrate that our method achieves new state-of-the-art performance on both synthetic and real-scanned datasets.