# Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors

arXiv: https://arxiv.org/abs/1609.01571 · HTML: https://mlsanity.com/paper/1609.01571/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2016.

## Built on by (most cited first, 12 of 12)

- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Learning Anatomically Consistent Embedding for Chest Radiography](https://mlsanity.com/paper/2312.00335/) (2023)
- [Clothes-Changing Person Re-identification Based On Skeleton Dynamics](https://mlsanity.com/paper/2503.10759/) (2025)
- [Learning ABCs: Approximate Bijective Correspondence for isolating factors of variation with weak supervision](https://mlsanity.com/paper/2103.03240/) (2021)
- [PhotoBot: Reference-Guided Interactive Photography via Natural Language](https://mlsanity.com/paper/2401.11061/) (2024)
- [DeepBBS: Deep Best Buddies for Point Cloud Registration](https://mlsanity.com/paper/2110.03016/) (2021)
- [NOCTIS: Novel Object Cyclic Threshold based Instance Segmentation](https://mlsanity.com/paper/2507.01463/) (2025)
- [Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour Fields](https://mlsanity.com/paper/2306.15010/) (2023)
- [Object-Level Targeted Selection via Deep Template Matching](https://mlsanity.com/paper/2207.01778/) (2022)
- [EOPose : Exemplar-based object reposing using Generalized Pose Correspondences](https://mlsanity.com/paper/2505.03394/) (2025)
- [Keypoint Counting Classifiers: Turning Vision Transformers into Self-Explainable Models Without Training](https://mlsanity.com/paper/2512.17891/) (2025)
- [Confidence-feedback-weighted graph matching network: online-offline laser-induced damage site matching under complex interference](https://mlsanity.com/paper/2606.29255/) (2026)

## Abstract (arXiv)

We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)--pairs of points in source and target sets, where each point is the nearest neighbor of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset while using different types of features.