Robust Feature Correspondence Through Locality-Preserving Global Consistency Optimization Under Occlusion
DOI:
https://doi.org/10.66238/tnks7448Keywords:
Feature Correspondence, Occlusion Handling, Global Consistency, Locality PreservationAbstract
The problem of feature correspondence is foundational to numerous computer vision applications, ranging from three-dimensional reconstruction to simultaneous localization and mapping. Despite significant advancements in the field, establishing robust feature matches under severe occlusion remains a formidable challenge. Occlusion disrupts the spatial continuity of feature sets, leading to high outlier ratios and structural ambiguities. This paper proposes a novel framework for robust feature correspondence through locality-preserving global consistency optimization. The proposed approach uniquely integrates local geometric structures with global topological constraints to disambiguate matches in heavily occluded scenes. By constructing a locality-preserving graph that models the immediate spatial neighborhood of features, the algorithm maintains structural fidelity even when large portions of the data are missing. Concurrently, a global consistency optimization module enforces rigid and non-rigid transformation constraints across the entire feature set, effectively filtering outliers and preserving structural integrity. Extensive theoretical analysis and empirical evaluations demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms in scenarios characterized by extensive partial visibility and structural interference. The findings provide a comprehensive theoretical foundation for integrating local and global spatial priors in feature matching paradigms.
References
1. Wang, Z., Kim, E. H., Oh, S. K., Pedrycz, W., Fu, Z., & Yoon, J. H. (2024). Reinforced fuzzy-rule-based neural networks realized through streamlined feature selection strategy and fuzzy clustering with distance variation. IEEE Transactions on Fuzzy Systems, 32(10), 5674-5686.
2. Wang, Y., Li, F. W., & Wang, J. (2026, May). Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition. In ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 10712-10716). IEEE.
3. Yao, Z., Li, R., Chen, X., Cheng, J., Le, C., Yue, M., ... & Dong, J. (2026). Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization. arXiv preprint arXiv:2607.25136.
4. Zhang, J., Shi, Y., Ma, Y., Xu, L., Yu, J., & Wang, J. (2023, June). Ikol: Inverse kinematics optimization layer for 3d human pose and shape estimation via gauss-newton differentiation. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 3, pp. 3454-3462).
5. Zhang, J., & Tang, H. (2025). Resolving Task Objective Conflicts in Unified Model via Task-Aware Mixture-of-Experts. arXiv preprint arXiv:2506.03591.
6. Jia, X., Wang, Q., Wang, A., Wang, H., Gyenes, B., Gospodinov, E., ... & Neumann, G. (2026). Pointmappolicy: Structured point cloud processing for multi-modal imitation learning. Advances in Neural Information Processing Systems, 38, 160188-160216.
7. Jin, H., Tsai, F. S., & Martinez-Vazquez, J. (2025). Optimal expenditure decentralization for sustainable development: evidence from a 52-country panel analysis. Financial Innovation, 11(1), 111.
8. Wang, Y., Yu, H., Tang, J., Gao, Y., Wang, X., Yue, Y., & Yang, Y. (2026). FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian Splatting. arXiv preprint arXiv:2603.23891.
9. Mur-Artal, R., & Tardós, J. D. (2017). ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras. IEEE Transactions on Robotics, 33(5), 1255–1262.
10. Zhu, R., Jiang, B., Mei, L., Yang, F., Wang, L., Gao, H., ... & Zhang, D. (2025). Adaptflow: Adaptive workflow optimization via meta-learning. arXiv preprint arXiv:2508.08053.
11. Hu, H., Yang, Y., Zhao, Q., & Zhang, C. (2022, June). On the role of discount factor in offline reinforcement learning. In International conference on machine learning (pp. 9072-9098). PMLR.
12. Cong, P., Xu, Y., Ren, Y., Zhang, J., Xu, L., Wang, J., ... & Ma, Y. (2023, June). Weakly supervised 3d multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 1, pp. 461-469).
13. Wang, Y., Zhang, S., Ye, J., Peng, H., & Sun, L. (2024, October). A mixed-curvature graph diffusion model. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (pp. 2482-2492).
14. Zhang, S., Xu, J., Huang, E., Chen, C. H., & Gao, S. (2016, March). Improving ordinal transformation through optimal combination of multi-model predictions. In 2016 IEEE International Conference on Industrial Technology (ICIT) (pp. 1545-1549). IEEE.
15. Fan, J., Liang, Y., Liu, L., Huang, S., & Zhang, L. (2023). RCA-NOC: Relative contrastive alignment for novel object captioning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 15510–15520). IEEE. https://doi.org/10.1109/ICCV51070.2023.01422
16. Sang, Y. (2026, March). Adaptive Quantization Strategies for Robust ML Inference Under Distribution Shift. In Proceedings of the 2026 5th International Conference on Cyber Security, Artificial Intelligence and Digital Economy (pp. 362-368).
17. Wu, J., Chen, S., Heo, I., Gutfraind, S., Liu, S., Li, C., ... & Sharps, M. (2025). Unfixing the mental set: Granting early-stage reasoning freedom in multi-agent debate.
18. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of CVPR.
19. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024, June). A conditional denoising diffusion probabilistic model for point cloud upsampling. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 20786-20795). IEEE.
20. Liu, W., Gao, S., & Lee, L. H. (2017, December). A multi-objective perspective on robust ranking and selection. In 2017 Winter Simulation Conference (WSC) (pp. 2116-2127). IEEE.
21. Wang, X., Zhang, L., Pu, H., Qureshi, A. H., & Li, H. (2026, April). Continuous-time value iteration for multi-agent reinforcement learning. In International Conference on Learning Representations (Vol. 2026, pp. 93980-93999).
22. Zhang, J., Luo, H., Yang, H., Xu, X., Wu, Q., Shi, Y., ... & Wang, J. (2023). Neuraldome: A neural modeling pipeline on multi-view human-object interactions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8834-8845).
23. Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
24. Gao, S., Shi, L., & Zhang, Z. (2018). A peak-over-threshold search method for global optimization. Automatica, 89, 83-91.
25. M. Emani et al., ‘‘A comprehensive evaluation of novel AI accelerators
for deep learning workloads,’’ in Proc. IEEE/ACM Int. Workshop
Perform. Modeling, Benchmarking Simulation High Perform. Com_x0002_put. Syst. (PMBS), Nov. 2022, pp. 13–25.
26. Li, Y., Tan, G., & Gou, C. (2024). Cascaded iterative transformer for jointly predicting facial landmark, occlusion probability and head pose. International Journal of Computer Vision, 132(4), 1242-1257.
27. Lyu, S., Mao, S., & Ma, Y. (2025). Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising. arXiv preprint arXiv:2511.03272.
28. Li, Q., Luo, T., Jiang, M., Jiang, Z., Hou, C., & Li, F. (2025, April). Semi-supervised multi-view multi-label learning with view-specific transformer and enhanced pseudo-label. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 17, pp. 18430-18438).
29. Liu, H., & Henao, R. (2025, April). Learning to substitute words with model-based score ranking. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (pp. 11551-11565).
30. Leung, P. H., Wang, F., Li, Z., He, Z., Peng, Y., & Yang, W. F. (2026). Augmented Reality Integration Improves Ergonomics in Dynamic Navigation for Dental Implant Surgery. Journal of the Society for Information Display, 34(5), 428-435.
31. Liu, Y., Cai, Q., Wang, C., Yang, J., Fan, H., Dong, J., & Chen, S. (2024). Geometry-enhanced attentive multi-view stereo for challenging matching scenarios. IEEE Transactions on Circuits and Systems for Video Technology, 34(8), 7401-7416.
32. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception architecture for computer vision. In Proceedings of CVPR.
33. Yao, Y., Zhang, J., Miao, P., Zhang, L., Chen, G., Shu, F., & Wong, K. K. (2025). Hybrid RIS-enhanced ISAC secure systems: Joint optimization in the presence of an extended target. IEEE Transactions on Communications.
34. Jing, G., Gao, P., Lee, Y., Hu, Y., & Zhang, H. (2025). 3D-aided pedestrian representation learning for video-based person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 35 (12), 12830-12845.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aiden J. Wright, Olivia Roberts (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the International Journal of Machine Learning and Engineering (IJMLE) are licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, adaptation, and commercial use in any medium or format, provided the original author(s) and the source are properly credited.
Authors retain the copyright of their work while granting the journal the right of first publication.
To view a copy of this license, please visit:
https://creativecommons.org/licenses/by/4.0/
