A Multi-View Stereo Algorithm Based on Homogeneous Direct Spatial Expansion with Improved Reconstruction Accuracy and Completeness
Source abstract
Abstract
Reconstruction of 3D structures from multiple 2D images has wide applications in such fields as computer vision, cultural heritage preservation, etc. This paper presents a novel multi-view stereo algorithm based on homogeneous direct spatial expansion (MVS-HDSE) with high reconstruction accuracy and completeness. It adopts many unique measures in each step of reconstruction, including initial seed point extraction using the DAISY descriptor to increase the number of initial sparse seed points, homogeneous direct spatial expansion to enhance efficiency, initial value modification via a conditional-double-surface-fitting method before optimization and adaptive consistency filtering after optimization to ensure high accuracy, processing using a multi-level image pyramid to further improve completeness and efficiency, etc. As demonstrated by experiments, owing to above measures the proposed algorithm attained much improved reconstruction completeness and accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Vision and Imaging · 3D Surveying and Cultural Heritage · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Physical Science and Technology, Central China Normal University, Wuhan 430079, China
School of Electronic Information and Electrical Engineering, Xiangnan University, Chenzhou 423000, China
References (30)
Show source-provided references
1. Large-scale data for multiple-view stereopsis10.1007/s11263-016-0902-9 ↗
2. Jensen, R., Dahl, A., Vogiatzis, G., Tola, E., and Aanaes, H. (2014, January 23–28). Large Scale Multi-view Stereopsis Evaluation. Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.59 ↗
3. Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., and Szeliski, R. (2006, January 17–22). A Comparison and Evaluation of Multi-view Stereo Reconstruction Algorithms. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA.
4. Photo tourism: exploring photo collections in 3D10.1145/1141911.1141964 ↗
5. Photorealistic scene reconstruction by voxel coloring10.1023/A:1008176507526 ↗
6. A theory of shape by space carving10.1023/A:1008191222954 ↗
7. Multi-view stereo reconstruction of dense shape and complex appearance10.1007/s11263-005-6876-7 ↗
8. Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency10.1109/TPAMI.2007.70712 ↗
9. Kolmogorov, V., and Zabih, R. (2002, January 28–31). Multi-camera Scene Reconstruction via Graph Cuts. Proceedings of the 7th European Conference on Computer Vision, Copenhagen, Denmark.10.1007/3-540-47977-5_6 ↗
10. Goesele, M., Curless, B., and Seitz, S.M. (2006, January 17–22). Multi-view Stereo Revisited. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA.
11. Campbell, N.D., Vogiatzis, G., Hernandez, C., and Cipolla, R. (2008, January 12–18). Using Multiple Hypotheses to Improve Depth-maps for Multi-view Stereo. Proceedings of the 10th European Conference on Computer Vision, Marseille, France.10.1007/978-3-540-88682-2_58 ↗
12. Efficient large-scale multi-view stereo for ultra high-resolution image sets10.1007/s00138-011-0346-8 ↗
13. “Region-growing” algorithm for matching of terrain images10.1016/0262-8856(89)90001-2 ↗
14. Goesele, M., Snavely, N., Curless, B., Hoppe, H., and Seitz, S.M. (2007, January 14–20). Multiview Stereo for Community Photo Collections. Proceedings of the 11th International Conference on Computer Vision, Rio de Janeiro, Brazil.10.1109/ICCV.2007.4408933 ↗
15. Habbecke, M., and Kobbelt, L. (2007, January 17–22). A Surface-growing Approach to Multi-view Stereo Reconstruction. Proceedings of 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.10.1109/CVPR.2007.383195 ↗
16. Accurate, dense, and robust multiview stereopsis10.1109/TPAMI.2009.161 ↗
17. Kazhdan, M., Bolitho, M., and Hoppe, H. (2006, January 26–28). Poisson Surface Reconstruction. Proceedings of the fourth Eurographics Symposium on Geometry Processing, Cagliari, Italy.
18. Chen, L.C., Hoang, D.C., Lin, H.I., and Nguyen, T.H. (2016). Innovative methodology for multi-view point cloud registration in robotic 3D object scanning and reconstruction. Appl. Sci., 6.10.3390/app6050132 ↗
19. Strecha, C., Fransens, R., and Gool, L.V. (2006, January 17–22). Combined depth and outlier estimation in multi-view stereo. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA.
20. DAISY: An efficient dense descriptor applied to wide-baseline stereo10.1109/TPAMI.2009.77 ↗
21. Frahm, J.M., George, P., Gallup, D., Johnson, T., Raguram, R., Wu, C., Jen, Y.H., Dunn, E., Clipp, B., and Lazebnik, S. (2010, January 5–11). Building Rome on A Cloudless Day. Proceedings of the 11th European Conference on Computer Vision, Heraklion, Crete, Greece.10.1007/978-3-642-15561-1_27 ↗
22. Generating Absolute-Scale Point Cloud Data of Built Infrastructure Scenes Using a Monocular Camera Setting10.1061/(ASCE)CP.1943-5487.0000414 ↗
23. Innovative Stereo Vision-Based Approach to Generate Dense Depth Map of Transportation Infrastructure10.3141/2215-10 ↗
24. Progressive 3D Reconstruction of Infrastructure with Videogrammetry10.1016/j.autcon.2011.03.005 ↗
25. Adaptive least squares correlation: A powerful image matching technique
26. Mve-an image-based reconstruction environment10.1016/j.cag.2015.09.003 ↗
27. Wu, C. (July, January 29). Towards Linear-time Incremental Structure From Motion. Proceedings of 2013 International Conference on 3D Vision, Seattle, WA, USA.10.1109/3DV.2013.25 ↗
28. Distinctive image features from scale-invariant keypoints10.1023/B:VISI.0000029664.99615.94 ↗
29. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography10.1145/358669.358692 ↗
30. Efficiently building a matrix to rotate one vector to another10.1080/10867651.1999.10487509 ↗