# Multi-Image Semantic Matching by Mining Consistent Features

arXiv: https://arxiv.org/abs/1711.07641 · HTML: https://mlsanity.com/paper/1711.07641/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2017.

## Built on by (most cited first, 13 of 13)

- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [Quantum Permutation Synchronization](https://mlsanity.com/paper/2101.07755/) (2021)
- [Quantum Motion Segmentation](https://mlsanity.com/paper/2203.13185/) (2022)
- [Fast, Accurate and Memory-Efficient Partial Permutation Synchronization](https://mlsanity.com/paper/2203.16505/) (2022)
- [Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching](https://mlsanity.com/paper/2201.04797/) (2022)
- [A-ACT: Action Anticipation through Cycle Transformations](https://mlsanity.com/paper/2204.00942/) (2022)
- [Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition](https://mlsanity.com/paper/2101.05018/) (2021)
- [Structured Prediction Problem Archive](https://mlsanity.com/paper/2202.03574/) (2022)
- [Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections](https://mlsanity.com/paper/2103.17229/) (2021)
- [Learning Universe Model for Partial Matching Networks over Multiple Graphs](https://mlsanity.com/paper/2210.10374/) (2022)
- [Population-wise Labeling of Sulcal Graphs using Multi-graph Matching](https://mlsanity.com/paper/2301.13532/) (2023)
- [Non-Negative Spherical Relaxations for Universe-Free Multi-Matching and Clustering](https://mlsanity.com/paper/2310.13311/) (2023)
- [Contrastive General Graph Matching with Adaptive Augmentation Sampling](https://mlsanity.com/paper/2406.17199/) (2024)

## Abstract (arXiv)

This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a sparse set of reliable features in the image collection. In this way, the proposed method is able to prune nonrepeatable features and also highly scalable to handle thousands of images. We additionally propose a low-rank constraint to ensure the geometric consistency of feature correspondences over the whole image collection. Besides the competitive performance on multi-graph matching and semantic flow benchmarks, we also demonstrate the applicability of the proposed method for reconstructing object-class models and discovering object-class landmarks from images without using any annotation.