Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching
Not on the map. Why?
Abstract (arXiv)
Most image matching methods perform poorly when encountering large scale changes in images. To solve this problem, firstly, we propose a scale-difference-aware image matching method (SDAIM) that reduces image scale differences before local feature extraction, via resizing both images of an image pair according to an estimated scale ratio. Secondly, in order to accurately estimate the scale ratio, we propose a covisibility-attention-reinforced matching module (CVARM) and then design a novel neural network, termed as Scale-Net, based on CVARM. The proposed CVARM can lay more stress on covisible areas within the image pair and suppress the distraction from those areas visible in only one image. Quantitative and qualitative experiments confirm that the proposed Scale-Net has higher scale ratio estimation accuracy and much better generalization ability compared with all the existing scale ratio estimation methods. Further experiments on image matching and relative pose estimation tasks demonstrate that our SDAIM and Scale-Net are able to greatly boost the performance of representative local features and state-of-the-art local feature matching methods.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 20 Dec 2021.
Builds on
28 of 52 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
- 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
- 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
- 2016LIFT: Learned Invariant Feature Transformcited by 306
- 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
- 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
- 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
16 more
- 2017Learning to Find Good Correspondencescited by 176
- 2018LF-Net: Learning Local Features from Imagescited by 151
- 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 149
- 2017Convolutional neural network architecture for geometric matchingcited by 138
- 2017Graph-Cut RANSACcited by 133
- 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
- 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
- 2018MAGSAC: marginalizing sample consensuscited by 123
- 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
- 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
- 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
- 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
- 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
- 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
- 2019RF-Net: An End-to-End Image Matching Network based on Receptive Fieldcited by 22
- 2020Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddingscited by 16
Built on by
Citing papers per year: 2024: 1.
1 paper.