# Matchable Image Retrieval by Learning from Surface Reconstruction

arXiv: https://arxiv.org/abs/1811.10343 · HTML: https://mlsanity.com/paper/1811.10343/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2018.

## Built on by (most cited first, 19 of 19)

- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [DreamEditor: Text-Driven 3D Scene Editing with Neural Fields](https://mlsanity.com/paper/2306.13455/) (2023)
- [Learning to Match Features with Seeded Graph Matching Network](https://mlsanity.com/paper/2108.08771/) (2021)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [Deep Learning for Instance Retrieval: A Survey](https://mlsanity.com/paper/2101.11282/) (2021)
- [MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model](https://mlsanity.com/paper/2411.16157/) (2024)
- [A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation](https://mlsanity.com/paper/2508.09977/) (2025)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning](https://mlsanity.com/paper/2208.02053/) (2022)
- [3MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching](https://mlsanity.com/paper/2404.00838/) (2024)
- [Learning Feature Matching via Matchable Keypoint-Assisted Graph Neural Network](https://mlsanity.com/paper/2307.01447/) (2023)
- [On-the-Fly SfM: What you capture is What you get](https://mlsanity.com/paper/2309.11883/) (2023)
- [DRKF: Distilled Rotated Kernel Fusion for Efficient Rotation Invariant Descriptors in Local Feature Matching](https://mlsanity.com/paper/2209.10907/) (2022)
- [AMatFormer: Efficient Feature Matching via Anchor Matching Transformer](https://mlsanity.com/paper/2305.19205/) (2023)
- [ResMatch: Residual Attention Learning for Local Feature Matching](https://mlsanity.com/paper/2307.05180/) (2023)
- [SupScene: Scene-Structured Overlap Supervision for Image Retrieval in Unconstrained SfM](https://mlsanity.com/paper/2601.11930/) (2026)
- [SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms](https://mlsanity.com/paper/2208.09896/) (2022)
- [UAVPairs: A Challenging Benchmark for Match Pair Retrieval of Large-scale UAV Images](https://mlsanity.com/paper/2505.22098/) (2025)
- [SAMatcher: Dense Co-Visibility Modeling via Cross-View Fusion for Scale-Imbalance Image Matching](https://mlsanity.com/paper/2606.03406/) (2026)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In this paper, we narrow down this gap by presenting an efficient CNN-based method to retrieve images with overlaps, which we refer to as the matchable image retrieval problem. Different from previous methods that generates training data based on sparse reconstruction, we create a large-scale image database with rich 3D geometrics and exploit information from surface reconstruction to obtain fine-grained training data. We propose a batched triplet-based loss function combined with mesh re-projection to effectively learn the CNN representation. The proposed method significantly accelerates the image retrieval process in 3D reconstruction and outperforms the state-of-the-art CNN-based and BoW methods for matchable image retrieval. The code and data are available at https://github.com/hlzz/mirror.