Improved HardNet and Stricter Outlier Filtering to Guide Reliable Matching
Source abstract
Abstract
As the fundamental problem in the computer vision area, image matching has wide applications in pose estimation, 3D reconstruction, image retrieval, etc. Suffering from the influence of external factors, the process of image ... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Robotics and Sensor-Based Localization · Advanced Image and Video Retrieval Techniques · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (37)
Show source-provided references
1. Learning to find good correspondences
2. Learning two-view correspondences and geometry using orderaware network
3. Hartley · Multiple View Geometry in Computer Vision · 2004 · 1 · i
4. Automatic panoramic image stitching using invariant features10.1007/s11263-006-0002-3 ↗
5. D2-net: A trainable cnn for joint description and detection of local features
6. J. Revaud, P. Weinzaepfel, C. De Souza, N. Pion, G. Csurka et al., “R2d2: Repeatable and reliable detector and descriptor,” arXiv preprint arXiv:1906.06195, 2019.
7. Beyond cartesian representations for local descriptors
8. Leveraging local planar motion property for robust visual matching and localization10.1109/LRA.2022.3184797 ↗
9. A template matching based feature extraction for activity recognition10.32604/cmc.2022.024760 ↗
10. A stricter constraint produces outstanding matching: Learning reliable image matching with a quadratic hinge triplet loss network
11. A. Mishchuk, D. Mishkin, F. Radenovic and J. Matas, “Working hard to know your neighbor’s margins: Local descriptor learning loss,” arXiv preprint arXiv:1705.10872, 2017.
12. Image matching across wide baselines: From paper to practice10.1007/s11263-020-01385-0 ↗
13. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
14. Three things everyone should know to improve object retrieval
15. Surf: Speeded up robust features
16. Orb: An efficient 113 alternative to sift or surf
17. Fast explicit diffusion for accelerated 106 features in nonlinear scale spaces
18. Contextdesc: Local descriptor augmentation with cross-modality context
19. Sosnet: Second order similarity regularization for local descriptor learning
20. Y. Liu, Z. Shen, Z. Lin, S. Peng, H. Bao et al., “Gift: Learning transformation-invariant dense visual descriptors via group cnns,” arXiv preprint arXiv:1911.05932, 2019.
21. Tilde: A temporally invariant learned detector
22. Quad-networks: Unsupervised learning to rank for interest point detection
23. Key.net: Keypoint detection by handcrafted and learned cnn filters
24. Superpoint: Self-supervised interest point detection and description
25. Large-scale image retrieval with attentive deep local features
26. Gms: Grid-based motion statistics for fast, ultra-robust feature correspondence
27. Pointnet: Deep learning on point sets for 3d classification and segmentation
28. Local context normalization: Revisiting local normalization
29. Registration of terrestrial lidar and panoramic imagery using the spherical epipolar line and spherical absolute orientation model10.1109/JSEN.2022.3175621 ↗
30. H. Tan, X. Liu, B. Yin and X. Li, “Dr-gan: Distribution regularization for text-to-image generation,” arXiv preprint arXiv: 2204.07945, 2022.10.1109/TNNLS.2022.3165573 ↗
31. Novel image caption system using deep convolutional neural networks (vgg16)
32. Deep fundamental matrix estimation
33. Large-scale machine learning with stochastic gradient descent
34. Pytorch: An imperative style, high-performance deep learning library
35. Mitotic spindle positioning (misp) is an actin bundler that selectively stabilizes the rootlets of epithelial microvilli
36. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography10.1145/358669.358692 ↗
37. L. Cavalli, V. Larsson, M. R. Oswald, T. Sattler and M. Pollefeys, “Adalam: Revisiting handcrafted outlier detection,” arXiv preprint arXiv:2006.04250, 2020.10.1007/978-3-030-58529-7_45 ↗