# CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning

arXiv: https://arxiv.org/abs/2507.11834 · HTML: https://mlsanity.com/paper/2507.11834/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 25 of 25)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [Flowformer: Linearizing Transformers with Conservation Flows](https://mlsanity.com/paper/2202.06258/) (2022)
- [Hard Mixtures of Experts for Large Scale Weakly Supervised Vision](https://mlsanity.com/paper/1704.06363/) (2017)
- [Task-Customized Mixture of Adapters for General Image Fusion](https://mlsanity.com/paper/2403.12494/) (2024)
- [Progressive Correspondence Pruning by Consensus Learning](https://mlsanity.com/paper/2101.00591/) (2021)
- [A Decomposition Model for Stereo Matching](https://mlsanity.com/paper/2104.07516/) (2021)
- [BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruning](https://mlsanity.com/paper/2401.03459/) (2024)
- [MGNet: Learning Correspondences via Multiple Graphs](https://mlsanity.com/paper/2401.04984/) (2024)
- [3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation](https://mlsanity.com/paper/2501.16698/) (2025)
- [VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning](https://mlsanity.com/paper/2312.08774/) (2023)
- [CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning](https://mlsanity.com/paper/2408.08134/) (2024)

## Built on by (most cited first, 1 of 1)

- [GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry](https://mlsanity.com/paper/2508.00592/) (2025)

## Abstract (arXiv)

Establishing reliable correspondences between image pairs is a fundamental task in computer vision, underpinning applications such as 3D reconstruction and visual localization. Although recent methods have made progress in pruning outliers from dense correspondence sets, they often hypothesize consistent visual domains and overlook the challenges posed by diverse scene structures. In this paper, we propose CorrMoE, a novel correspondence pruning framework that enhances robustness under cross-domain and cross-scene variations. To address domain shift, we introduce a De-stylization Dual Branch, performing style mixing on both implicit and explicit graph features to mitigate the adverse influence of domain-specific representations. For scene diversity, we design a Bi-Fusion Mixture of Experts module that adaptively integrates multi-perspective features through linear-complexity attention and dynamic expert routing. Extensive experiments on benchmark datasets demonstrate that CorrMoE achieves superior accuracy and generalization compared to state-of-the-art methods. The code and pre-trained models are available at https://github.com/peiwenxia/CorrMoE.