Hierarchical Guided-Image-Filtering for Efficient Stereo Matching
Source abstract
Abstract
Stereo matching is complicated by the uneven distribution of textures on the image pairs. We address this problem by applying the edge-preserving guided-Image-filtering (GIF) at different resolutions. In contrast to most multi-scale stereo matching algorithms, parameters of the proposed hierarchical GIF model are in an innovative weighted-combination scheme to generate an improved matching cost volume. Our method draws its strength from exploiting texture in various resolution levels and performing an effective mixture of the derived parameters. This novel approach advances our recently proposed algorithm, the pervasive guided-image-filtering scheme, by equipping it with hierarchical filtering modules, leading to disparity images with more details. The approach ensures as many different-scale patterns as possible to be involved in the cost aggregation and hence improves matching accuracy. The experimental results show that the proposed scheme achieves the best matching accuracy when compared with six well-recognized cutting-edge algorithms using version 3 of the Middlebury stereo evaluation data sets.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Vision and Imaging · Image Enhancement Techniques · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Microelectronics, Tianjin University, Tianjin 300072, China
Department of Mechanical Engineering, Chang Gung University, Taoyuan 33302, Taiwan
Department of Neurosurgery, Chang Gung Memorial Hospital, Taoyuan 33305, Taiwan
Funding
The Ministry of Science and Technology, Taiwan · Chang Gung Memorial Hospital, Taiwan
References (31)
Show source-provided references
1. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms10.1023/A:1014573219977 ↗
2. Stereo matching by training a convolutional neural network to compare image patches
3. A learned sparseness and IGMRF-based regularization framework for dense disparity estimation using unsupervised feature learning
4. Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., and Brox, T. (2016, January 27–30). A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.438 ↗
5. Pang, J., Sun, W., Ren, J.S., Yang, C., and Yan, Q. (2017, January 22–29). Cascade residual learning: A two-stage convolutional neural network for stereo matching. Proceedings of the IEEE International Conference on Computer Vision Workshops, Venice, Italy.10.1109/ICCVW.2017.108 ↗
6. Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., and Bry, A. (2017, January 22–29). End-to-end learning of geometry and context for deep stereo regression. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.17 ↗
7. Chang, J.R., and Chen, Y.S. (2018, January 18–22). Pyramid stereo matching network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00567 ↗
8. Deep self-guided cost aggregation for stereo matching10.1016/j.patrec.2018.07.010 ↗
9. Novel belief propagation algorithm for stereo matching with a robust cost computation10.1109/ACCESS.2019.2902249 ↗
10. As-global-as-possible stereo matching with adaptive smoothness prior10.1049/iet-ipr.2018.5801 ↗
11. Stereo correspondence using efficient hierarchical belief propagation10.1007/s00521-012-0831-7 ↗
12. Stereo matching using weighted dynamic programming on a single-direction four-connected tree10.1016/j.cviu.2012.04.003 ↗
13. Sparse representation over discriminative dictionary for stereo matching10.1016/j.patcog.2017.06.015 ↗
14. Adaptive support-weight approach for correspondence search10.1109/TPAMI.2006.70 ↗
15. Stereo matching using tree filtering10.1109/TPAMI.2014.2353642 ↗
16. Domain transformation-based efficient cost aggregation for local stereo matching10.1109/TCSVT.2012.2223794 ↗
17. An efficient recursive edge-aware filter10.1016/j.image.2014.07.005 ↗
18. Full-image guided filtering for fast stereo matching10.1109/LSP.2013.2241759 ↗
19. Fast cost-volume filtering for visual correspondence and beyond10.1109/TPAMI.2012.156 ↗
20. Guided image filtering10.1109/TPAMI.2012.213 ↗
21. Weighted guided image filtering
22. Gradient domain guided image filtering10.1109/TIP.2015.2468183 ↗
23. A local stereo matching algorithm based on weighted guided-Image-filtering for improving the generation of depth range images10.1016/j.displa.2017.07.006 ↗
24. Local stereo matching algorithm with efficient matching cost and adaptive guided image filter10.1007/s00371-016-1264-6 ↗
25. Efficient stereo matching based on pervasive guided image filtering
26. Hu, W., Zhang, K., Sun, L., and Yang, S. (2013, January 15–19). Comparisons reducing for local stereo matching using hierarchical structure. Proceedings of the IEEE International Conference on Multimedia and Expo, San Jose, CA, USA.10.1109/ICME.2013.6607443 ↗
27. Robust multiscale stereo matching from fundus images with radiometric differences10.1109/TPAMI.2011.69 ↗
28. Li, R., Ham, B., Oh, C., and Sohn, K. (2013, January 19–21). Disparity search range estimation based on dense stereo matching. Proceedings of the IEEE Conference on Industrial Electronics and Applications, Melbourne, Australia.
29. Zhang, K., Fang, Y., Min, D., Sun, L., Yang, S., Yan, S., and Tian, Q. (2014, January 23–28). Cross-scale cost aggregation for stereo matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.206 ↗
30. Moritz, M., and Geiger, A. (2015, January 8–10). Object Scene Flow for Autonomous Vehicles. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.
31. Scharstein, D., Hirschmüller, H., Kitajima, Y., Krathwohl, G., Nesic, N., Wang, X., and Westling, P. (2014, January 12–15). High-resolution stereo datasets with subpixel-accurate ground truth. Proceedings of the German Conference on Pattern Recognition (GCPR 2014), Münster, Germany.10.1007/978-3-319-11752-2_3 ↗