# 3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching

arXiv: https://arxiv.org/abs/2207.02375 · HTML: https://mlsanity.com/paper/2207.02375/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 6 Jul 2022.

## Builds on (most cited first, 30 of 38)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [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)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Net2Net: Accelerating Learning via Knowledge Transfer](https://mlsanity.com/paper/1511.05641/) (2015)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Cross Modal Distillation for Supervision Transfer](https://mlsanity.com/paper/1507.00448/) (2015)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [Distilling Knowledge from Graph Convolutional Networks](https://mlsanity.com/paper/2003.10477/) (2020)
- [Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness](https://mlsanity.com/paper/1608.05842/) (2016)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)

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

- [PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment](https://mlsanity.com/paper/2306.15667/) (2023)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [LiftFeat: 3D Geometry-Aware Local Feature Matching](https://mlsanity.com/paper/2505.03422/) (2025)
- [RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges](https://mlsanity.com/paper/2502.19955/) (2025)
- [OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matching](https://mlsanity.com/paper/2302.05846/) (2023)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Affine steerers for structured keypoint description](https://mlsanity.com/paper/2408.14186/) (2024)
- [PRISM: PRogressive dependency maxImization for Scale-invariant image Matching](https://mlsanity.com/paper/2408.03598/) (2024)
- [FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer](https://mlsanity.com/paper/2310.13605/) (2023)
- [Towards RGB-NIR Cross-modality Image Registration and Beyond](https://mlsanity.com/paper/2405.19914/) (2024)
- [Are Semi-Dense Detector-Free Methods Good at Matching Local Features?](https://mlsanity.com/paper/2402.08671/) (2024)
- [Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting](https://mlsanity.com/paper/2511.21265/) (2025)
- [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026)
- [DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models](https://mlsanity.com/paper/2608.23850/) (2026)

## Abstract (arXiv)

We tackle the essential task of finding dense visual correspondences between a pair of images. This is a challenging problem due to various factors such as poor texture, repetitive patterns, illumination variation, and motion blur in practical scenarios. In contrast to methods that use dense correspondence ground-truths as direct supervision for local feature matching training, we train 3DG-STFM: a multi-modal matching model (Teacher) to enforce the depth consistency under 3D dense correspondence supervision and transfer the knowledge to 2D unimodal matching model (Student). Both teacher and student models consist of two transformer-based matching modules that obtain dense correspondences in a coarse-to-fine manner. The teacher model guides the student model to learn RGB-induced depth information for the matching purpose on both coarse and fine branches. We also evaluate 3DG-STFM on a model compression task. To the best of our knowledge, 3DG-STFM is the first student-teacher learning method for the local feature matching task. The experiments show that our method outperforms state-of-the-art methods on indoor and outdoor camera pose estimations, and homography estimation problems. Code is available at: https://github.com/Ryan-prime/3DG-STFM.