# VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning

arXiv: https://arxiv.org/abs/2312.08774 · HTML: https://mlsanity.com/paper/2312.08774/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [Graph-Cut RANSAC](https://mlsanity.com/paper/1706.00984/) (2017)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [ContextDesc: Local Descriptor Augmentation with Cross-Modality Context](https://mlsanity.com/paper/1904.04084/) (2019)
- [Progressive Correspondence Pruning by Consensus Learning](https://mlsanity.com/paper/2101.00591/) (2021)
- [Learnable Motion Coherence for Correspondence Pruning](https://mlsanity.com/paper/2011.14563/) (2020)

## Built on by (most cited first, 8 of 8)

- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Scalable and Generalizable Correspondence Pruning via Geometry-Consistent Pre-training](https://mlsanity.com/paper/2406.05773/) (2024)
- [MGCA-Net: Multi-Graph Contextual Attention Network for Two-View Correspondence Learning](https://mlsanity.com/paper/2512.23369/) (2025)
- [CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning](https://mlsanity.com/paper/2408.08134/) (2024)
- [CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning](https://mlsanity.com/paper/2507.11834/) (2025)
- [GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry](https://mlsanity.com/paper/2508.00592/) (2025)
- [SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning](https://mlsanity.com/paper/2606.04493/) (2026)
- [See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning](https://mlsanity.com/paper/2606.09262/) (2026)

## Abstract (arXiv)

Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (eg texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks. Our code is provided at the following repository: https://github.com/sugar-fly/VSFormer.