# PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration

arXiv: https://arxiv.org/abs/2308.04782 · HTML: https://mlsanity.com/paper/2308.04782/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 75 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [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)
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://mlsanity.com/paper/2103.01458/) (2021)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Deep Global Registration](https://mlsanity.com/paper/2004.11540/) (2020)
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://mlsanity.com/paper/2203.08195/) (2022)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://mlsanity.com/paper/2003.03164/) (2020)
- [EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection](https://mlsanity.com/paper/2007.08856/) (2020)
- [Sequence to Sequence -- Video to Text](https://mlsanity.com/paper/1505.00487/) (2015)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://mlsanity.com/paper/2011.12149/) (2020)

## Built on by (most cited first, 14 of 14)

- [Diffusion Models are Open-World Affordance Learners: Leveraging Generative Priors for 3D Affordance Learning](https://mlsanity.com/paper/2508.01651/) (2025)
- [IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration](https://mlsanity.com/paper/2603.12719/) (2026)
- [RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration](https://mlsanity.com/paper/2405.07594/) (2024)
- [3D Registration in 30 Years: A Survey](https://mlsanity.com/paper/2412.13735/) (2024)
- [DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation](https://mlsanity.com/paper/2511.13047/) (2025)
- [CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition](https://mlsanity.com/paper/2407.17457/) (2024)
- [Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration](https://mlsanity.com/paper/2411.01870/) (2024)
- [2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition](https://mlsanity.com/paper/2505.09073/) (2025)
- [F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimization](https://mlsanity.com/paper/2405.00507/) (2024)
- [Multimodal surface defect detection from wooden logs for sawing optimization](https://mlsanity.com/paper/2503.21367/) (2025)
- [DINOReg: Strong Point Cloud Registration with Vision Foundation Model](https://mlsanity.com/paper/2509.24370/) (2025)
- [ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance](https://mlsanity.com/paper/2511.22908/) (2025)
- [Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration](https://mlsanity.com/paper/2512.09407/) (2025)
- [GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusion](https://mlsanity.com/paper/2604.17721/) (2026)

## Abstract (arXiv)

Point cloud registration is a task to estimate the rigid transformation between two unaligned scans, which plays an important role in many computer vision applications. Previous learning-based works commonly focus on supervised registration, which have limitations in practice. Recently, with the advance of inexpensive RGB-D sensors, several learning-based works utilize RGB-D data to achieve unsupervised registration. However, most of existing unsupervised methods follow a cascaded design or fuse RGB-D data in a unidirectional manner, which do not fully exploit the complementary information in the RGB-D data. To leverage the complementary information more effectively, we propose a network implementing multi-scale bidirectional fusion between RGB images and point clouds generated from depth images. By bidirectionally fusing visual and geometric features in multi-scales, more distinctive deep features for correspondence estimation can be obtained, making our registration more accurate. Extensive experiments on ScanNet and 3DMatch demonstrate that our method achieves new state-of-the-art performance. Code will be released at https://github.com/phdymz/PointMBF