mlsanityData to 14 Oct 2026

VMatcher: State-Space Semi-Dense Local Feature Matching

arXiv 2507.23371 ↗First posted 31 Jul 2025cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Vision Mamba backbones

Abstract (arXiv)

This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance but depend heavily on the Transformer's attention mechanism, which, while effective, incurs high computational costs due to its quadratic complexity. In contrast, Mamba introduces a Selective State-Space Model (SSM) that achieves comparable or superior performance with linear complexity, offering significant efficiency gains. VMatcher leverages a hybrid approach, integrating Mamba's highly efficient long-sequence processing with the Transformer's attention mechanism. Multiple VMatcher configurations are proposed, including hierarchical architectures, demonstrating their effectiveness in setting new benchmarks efficiently while ensuring robustness and practicality for real-time applications where rapid inference is crucial. Source Code is available at: https://github.com/ayoussf/VMatcher

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Vision Mamba backbones, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 26 of its 39 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

26 of 39 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbone10 Jul
  2. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba15 Mar

Other references · 24

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  7. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,336
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  11. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 608
  12. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
12 more
  1. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  2. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  3. 2020DISK: Learning local features with policy gradientcited by 312
  4. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  5. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  6. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  7. 2017Learning to Find Good Correspondencescited by 176
  8. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  9. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  10. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
  11. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 120
  12. 2023SiLK -- Simple Learned Keypointscited by 54

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba
  2. 2025MambaGlue: Fast and Robust Local Feature Matching With Mamba
  3. 2025Similarity-Aware Selective State-Space Modeling for Semantic Correspondence
  4. 2025VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
  5. 2025MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection
  6. 2024LocalMamba: Visual State Space Model with Windowed Selective Scan
  7. 2025A Separable Self-attention Inspired by the State Space Model for Computer Vision
  8. 2026SF-Mamba: Rethinking State Space Model for Vision