Single-image piecewise planar reconstruction of urban buildings based on geometric priors
文献类型：期刊论文
| 作者 | Wang, Wei2; Dong, Qiulei1,3 ; Hu, Zhanyi1,3
|
| 刊名 | ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
 |
| 出版日期 | 2023-10-01 |
| 卷号 | 204页码:105-116 |
| ISSN号 | 0924-2716 |
| 关键词 | Single-image 3D reconstruction Piecewise planar reconstruction Geometric prior Urban building Structure and proximity constraints |
| DOI | 10.1016/j.isprsjprs.2023.09.005 |
| 通讯作者 | Dong, Qiulei(qldong@nlpr.ia.ac.cn) |
| 英文摘要 | Single-image 3D urban building reconstruction is an important and challenging topic in computer vision. However, it is a highly ill-posed problem due to the intrinsic geometrical ambiguity in a 3D space. To address the problem, this paper presents a novel single-image piecewise planar reconstruction method based on geometric priors. The proposed method utilizes geometric priors (e.g., plane orientation and intersection angles between planes) learned through convolutional neural networks to handle three challenging subtasks sequentially: (1) detecting planar regions with structure information (e.g., each component edge is associated with two planes intersecting at a specified angle); (2) inferring the planes corresponding to the planar regions progressively by taking full advantage of diverse constraints (e.g., structure and proximity constraints) based on geometric priors; and (3) globally optimizing the resulting planes under a unified framework that incorporates image cues and geometric priors. Experimental results on two public datasets released by CASIA and our own dataset demonstrate that the proposed method significantly outperforms five state-of-the-art methods (including two geometrybased methods and three learning-based methods) by an approximately 20 % margin in terms of accuracy. Code and data are available at https://github.com/three-dimensional-computer-vision/single-image-reconstruction. |
| 资助项目 | National Natural Science Foundation of China[61991423] ; National Natural Science Foundation of China[U1805264] ; Key Scientific and Technological Project of Henan Province[232102321068] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27040811] |
| WOS研究方向 | Physical Geography ; Geology ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| 出版者 | ELSEVIER |
| WOS记录号 | WOS:001076302400001 |
| 资助机构 | National Natural Science Foundation of China ; Key Scientific and Technological Project of Henan Province ; Strategic Priority Research Program of the Chinese Academy of Sciences |
| 源URL | [http://ir.ia.ac.cn/handle/173211/53098]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Dong, Qiulei |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Zhoukou Normal Univ, Sch Network Engn, Zhoukou 466000, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Wei,Dong, Qiulei,Hu, Zhanyi. Single-image piecewise planar reconstruction of urban buildings based on geometric priors[J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,2023,204:105-116. |
| APA | Wang, Wei,Dong, Qiulei,&Hu, Zhanyi.(2023).Single-image piecewise planar reconstruction of urban buildings based on geometric priors.ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING,204,105-116. |
| MLA | Wang, Wei,et al."Single-image piecewise planar reconstruction of urban buildings based on geometric priors".ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 204(2023):105-116. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。