GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network
Not on the map. Why?
Abstract (arXiv)
Feature-based image matching has extensive applications in computer vision. Keypoints detected in images can be naturally represented as graph structures, and Graph Neural Networks (GNNs) have been shown to outperform traditional deep learning techniques. Consequently, the paradigm of image matching via GNNs has gained significant prominence in recent academic research. In this paper, we first introduce an innovative adaptive graph construction method that utilizes a filtering mechanism based on distance and dynamic threshold similarity. This method dynamically adjusts the criteria for incorporating new vertices based on the characteristics of existing vertices, allowing for the construction of more precise and robust graph structures while avoiding redundancy. We further combine the vertex processing capabilities of GNNs with the global awareness capabilities of Transformers to enhance the model's representation of spatial and feature information within graph structures. This hybrid model provides a deeper understanding of the interrelationships between vertices and their contributions to the matching process. Additionally, we employ the Sinkhorn algorithm to iteratively solve for optimal matching results. Finally, we validate our system using extensive image datasets and conduct comprehensive comparative experiments. Experimental results demonstrate that our system achieves an average improvement of 3.8x-40.3x in overall matching performance. Additionally, the number of vertices and edges significantly impacts training efficiency and memory usage; therefore, we employ multi-GPU technology to accelerate the training process. Our code is available at https://github.com/songxf1024/GIMS.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 54 references that are in the map. First posted on arXiv 24 Dec 2024.
Builds on
19 of 54 references.
References · 19
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
- 2023LightGlue: Local Feature Matching at Light Speedcited by 583
- 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
- 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
- 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
- 2017HashNet: Deep Learning to Hash by Continuationcited by 121
- 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
7 more
- 2021Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Losscited by 116
- 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
- 2015Feature Learning based Deep Supervised Hashing with Pairwise Labelscited by 59
- 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
- 2017Toward Geometric Deep SLAMcited by 38
- 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
- 2020Multilevel Graph Matching Networks for Deep Graph Similarity Learningcited by 29
Built on by
Citing papers per year: 2026: 1.
1 paper.