Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes
Multiview stereo (MVS) achieves efficient 3D reconstruction on Lambertian surfaces and strongly textured regions. However, the reconstruction of weakly textured regions, especially planar surfaces in weakly textured regions, still faces significant challenges due to the fuzzy matching problem of pho...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2474 |
| _version_ | 1797601751426138112 |
|---|---|
| author | Chuanyu Fu Nan Huang Zijie Huang Yongjian Liao Xiaoming Xiong Xuexi Zhang Shuting Cai |
| author_facet | Chuanyu Fu Nan Huang Zijie Huang Yongjian Liao Xiaoming Xiong Xuexi Zhang Shuting Cai |
| author_sort | Chuanyu Fu |
| collection | DOAJ |
| description | Multiview stereo (MVS) achieves efficient 3D reconstruction on Lambertian surfaces and strongly textured regions. However, the reconstruction of weakly textured regions, especially planar surfaces in weakly textured regions, still faces significant challenges due to the fuzzy matching problem of photometric consistency. In this paper, we propose a multiview stereo for recovering planar surfaces guided by confidence calculations, resulting in the construction of large-scale 3D models for high-resolution image scenes. Specifically, a confidence calculation method is proposed to express the reliability degree of plane hypothesis. It consists of multiview consistency and patch consistency, which characterize global contextual information and local spatial variation, respectively. Based on the confidence of plane hypothesis, the proposed plane supplementation generates new reliable plane hypotheses. The new planes are embedded in the confidence-driven depth estimation. In addition, an adaptive depth fusion approach is proposed to allow regions with insufficient visibility to be effectively fused into the dense point clouds. The experimental results illustrate that the proposed method can lead to a 3D model with competitive completeness and high accuracy compared with state-of-the-art methods. |
| first_indexed | 2024-03-11T04:08:07Z |
| format | Article |
| id | doaj.art-8fd6f0e599224c96a15790e99c6d66ba |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:07Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8fd6f0e599224c96a15790e99c6d66ba2023-11-17T23:40:40ZengMDPI AGRemote Sensing2072-42922023-05-01159247410.3390/rs15092474Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image ScenesChuanyu Fu0Nan Huang1Zijie Huang2Yongjian Liao3Xiaoming Xiong4Xuexi Zhang5Shuting Cai6School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Integrated Circuits, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Integrated Circuits, Guangdong University of Technology, Guangzhou 510006, ChinaMultiview stereo (MVS) achieves efficient 3D reconstruction on Lambertian surfaces and strongly textured regions. However, the reconstruction of weakly textured regions, especially planar surfaces in weakly textured regions, still faces significant challenges due to the fuzzy matching problem of photometric consistency. In this paper, we propose a multiview stereo for recovering planar surfaces guided by confidence calculations, resulting in the construction of large-scale 3D models for high-resolution image scenes. Specifically, a confidence calculation method is proposed to express the reliability degree of plane hypothesis. It consists of multiview consistency and patch consistency, which characterize global contextual information and local spatial variation, respectively. Based on the confidence of plane hypothesis, the proposed plane supplementation generates new reliable plane hypotheses. The new planes are embedded in the confidence-driven depth estimation. In addition, an adaptive depth fusion approach is proposed to allow regions with insufficient visibility to be effectively fused into the dense point clouds. The experimental results illustrate that the proposed method can lead to a 3D model with competitive completeness and high accuracy compared with state-of-the-art methods.https://www.mdpi.com/2072-4292/15/9/2474confidence calculationdepth estimationmultiview stereoplane supplementationweakly textured regions |
| spellingShingle | Chuanyu Fu Nan Huang Zijie Huang Yongjian Liao Xiaoming Xiong Xuexi Zhang Shuting Cai Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes Remote Sensing confidence calculation depth estimation multiview stereo plane supplementation weakly textured regions |
| title | Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes |
| title_full | Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes |
| title_fullStr | Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes |
| title_full_unstemmed | Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes |
| title_short | Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes |
| title_sort | confidence guided planar recovering multiview stereo for weakly textured plane of high resolution image scenes |
| topic | confidence calculation depth estimation multiview stereo plane supplementation weakly textured regions |
| url | https://www.mdpi.com/2072-4292/15/9/2474 |
| work_keys_str_mv | AT chuanyufu confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT nanhuang confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT zijiehuang confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT yongjianliao confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT xiaomingxiong confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT xuexizhang confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes AT shutingcai confidenceguidedplanarrecoveringmultiviewstereoforweaklytexturedplaneofhighresolutionimagescenes |