# NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences

arXiv: https://arxiv.org/abs/1904.00320 · HTML: https://mlsanity.com/paper/1904.00320/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2019.

## Built on by (most cited first, 29 of 29)

- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://mlsanity.com/paper/2203.14453/) (2022)
- [Progressive Correspondence Pruning by Consensus Learning](https://mlsanity.com/paper/2101.00591/) (2021)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement](https://mlsanity.com/paper/2209.12213/) (2022)
- [TurboReg: TurboClique for Robust and Efficient Point Cloud Registration](https://mlsanity.com/paper/2507.01439/) (2025)
- [DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration](https://mlsanity.com/paper/2112.14059/) (2021)
- [Two-View Geometry Scoring Without Correspondences](https://mlsanity.com/paper/2306.01596/) (2023)
- [MGNet: Learning Correspondences via Multiple Graphs](https://mlsanity.com/paper/2401.04984/) (2024)
- [Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty](https://mlsanity.com/paper/2104.08278/) (2021)
- [SIFT Matching by Context Exposed](https://mlsanity.com/paper/2106.09584/) (2021)
- [Joint Graph Learning and Matching for Semantic Feature Correspondence](https://mlsanity.com/paper/2109.00240/) (2021)
- [Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network](https://mlsanity.com/paper/2111.09006/) (2021)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Learning Second-Order Attentive Context for Efficient Correspondence Pruning](https://mlsanity.com/paper/2303.15761/) (2023)
- [Point-and-Shoot All-in-Focus Photo Synthesis from Smartphone Camera Pair](https://mlsanity.com/paper/2304.04917/) (2023)
- [A2B: Anchor to Barycentric Coordinate for Robust Correspondence](https://mlsanity.com/paper/2306.02760/) (2023)
- [Learning Probabilistic Coordinate Fields for Robust Correspondences](https://mlsanity.com/paper/2306.04231/) (2023)
- [Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences](https://mlsanity.com/paper/2102.00411/) (2021)
- [RGBD-Glue: General Feature Combination for Robust RGB-D Point Cloud Registration](https://mlsanity.com/paper/2405.07594/) (2024)
- [Local Consensus Enhanced Siamese Network with Reciprocal Loss for Two-view Correspondence Learning](https://mlsanity.com/paper/2308.03217/) (2023)
- [CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning](https://mlsanity.com/paper/2408.08134/) (2024)
- [Monte Carlo Diffusion for Generalizable Learning-Based RANSAC](https://mlsanity.com/paper/2503.09410/) (2025)
- [Understanding and Optimizing Attention-Based Sparse Matching for Diverse Local Features](https://mlsanity.com/paper/2602.08430/) (2026)
- [DVMNet++: Rethinking Relative Pose Estimation for Unseen Objects](https://mlsanity.com/paper/2403.13683/) (2024)
- [Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graph](https://mlsanity.com/paper/2408.15750/) (2024)
- [Dual-Camera All-in-Focus Neural Radiance Fields](https://mlsanity.com/paper/2504.16636/) (2025)
- [SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning](https://mlsanity.com/paper/2606.04493/) (2026)

## Abstract (arXiv)

Feature correspondence selection is pivotal to many feature-matching based tasks in computer vision. Searching for spatially k-nearest neighbors is a common strategy for extracting local information in many previous works. However, there is no guarantee that the spatially k-nearest neighbors of correspondences are consistent because the spatial distribution of false correspondences is often irregular. To address this issue, we present a compatibility-specific mining method to search for consistent neighbors. Moreover, in order to extract and aggregate more reliable features from neighbors, we propose a hierarchical network named NM-Net with a series of convolution layers taking the generated graph as input, which is insensitive to the order of correspondences. Our experimental results have shown the proposed method achieves the state-of-the-art performance on four datasets with various inlier ratios and varying numbers of feature consistencies.