MatchFormer: Interleaving Attention in Transformers for Feature Matching [PDF]
Asian Conference on Computer Vision, 2022 Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make ...
Qing Wang +4 more
semanticscholar +1 more source
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors [PDF]
ACM Multimedia, 2022 A key challenge of real-world image super-resolution (SR) is to recover the missing details in low-resolution (LR) images with complex unknown degradations (\eg, downsampling, noise and compression).
Chaofeng Chen +6 more
semanticscholar +1 more source
DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching [PDF]
Expert systems with applications, 2023 Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes.
Tao Xie +4 more
semanticscholar +1 more source
PATS: Patch Area Transportation with Subdivision for Local Feature Matching [PDF]
Computer Vision and Pattern Recognition, 2023 Local feature matching aims at establishing sparse correspondences between a pair of images. Recently, detector-free methods present generally better performance but are not satisfactory in image pairs with large scale differences.
Junjie Ni +6 more
semanticscholar +1 more source
Adaptive Spot-Guided Transformer for Consistent Local Feature Matching [PDF]
Computer Vision and Pattern Recognition, 2023 Local feature matching aims at finding correspondences between a pair of images. Although current detector-free methods leverage Transformer architecture to obtain an impressive performance, few works consider maintaining local consistency.
Jiahuan Yu +4 more
semanticscholar +1 more source
Feature Matching Data Synthesis for Non-IID Federated Learning [PDF]
IEEE Transactions on Mobile Computing, 2023 Federated learning (FL) has emerged as a privacy-preserving paradigm that trains neural networks on edge devices without collecting data at a central server.
Zijian Li +5 more
semanticscholar +1 more source
SuperGlue: Learning Feature Matching With Graph Neural Networks [PDF]
Computer Vision and Pattern Recognition, 2019 This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
Paul-Edouard Sarlin +3 more
semanticscholar +1 more source
ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching [PDF]
Computer Vision and Pattern Recognition, 2022 Graph Neural Networks (GNNs) with attention have been successfully applied for learning visual feature matching. However, current methods learn with complete graphs, resulting in a quadratic complexity in the number of features.
Yanxing Shi +5 more
semanticscholar +1 more source
DFNet: Enhance Absolute Pose Regression with Direct Feature Matching [PDF]
European Conference on Computer Vision, 2022 We introduce a camera relocalization pipeline that combines absolute pose regression (APR) and direct feature matching. By incorporating exposure-adaptive novel view synthesis, our method successfully addresses photometric distortions in outdoor ...
Shuai Chen +3 more
semanticscholar +1 more source
DeDoDe: Detect, Don’t Describe — Describe, Don’t Detect for Local Feature Matching [PDF]
International Conference on 3D Vision, 2023 Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consistent between views, i.e., correspond to the same 3D point in the scene.
Johan Edstedt +3 more
semanticscholar +1 more source