BROWSE
Detail
Journal Article
Enhanced Soft 3D Reconstruction Method with an Iterative Matching Cost Update Using Object Surface Consensus
- Authors
- Min-Jae Lee, Gi-Mun Um, Joungil Yun, Won-Sik Cheong, Soon-Yong Park
- Issue Date
- 2021-10
- Citation
- Sensors, v.21, no.19, pp.1-24
- ISSN
- 1424-8220
- Publisher
- MDPI
- Language
- English
- Type
- Journal Article
- Abstract
- In this paper, we propose a multi?릚iew stereo matching method, EnSoft3D (Enhanced Soft 3D Reconstruction) to obtain dense and high?릕uality depth images. Multi?릚iew stereo is one of the high?릋nterest research areas and has wide applications. Motivated by the Soft3D reconstruction method, we introduce a new multi?릚iew stereo matching scheme. The original Soft3D method is introduced for novel view synthesis, while occlusion?륾ware depth is also reconstructed by integrating the matching costs of the Plane Sweep Stereo (PSS) and soft visibility volumes. However, the Soft3D method has an inherent limitation because the erroneous PSS matching costs are not up-dated. To overcome this limitation, the proposed scheme introduces an update process of the PSS matching costs. From the object surface consensus volume, an inverse consensus kernel is derived, and the PSS matching costs are iteratively updated using the kernel. The proposed EnSoft3D method reconstructs a highly accurate 3D depth image because both the multi?릚iew matching cost and soft visibility are updated simultaneously. The performance of the proposed method is evaluated by using structured and unstructured benchmark datasets. Disparity error is measured to verify 3D reconstruction accuracy, and both PSNR and SSIM are measured to verify the simultaneous enhancement of view synthesis.
- KSP Keywords
- 3D depth, 3d reconstruction, Benchmark datasets, Depth image, Highly accurate, Matching costs, Novel view synthesis, Plane Sweep, Reconstruction accuracy, Reconstruction method, Verify 3D
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
