Realistic Procedural Plant Modeling from Multiple View Images
文献类型：期刊论文
| 作者 | Jianwei Guo ; Shibiao Xu; Dong-Ming Yan; Zhanglin Cheng; Marc Jaeger; Xiaopeng Zhang
|
| 刊名 | IEEE Transactions on Visualization and Computer Graphics
 |
| 出版日期 | 2018-09-24 |
| 卷号 | xx期号:xx页码:xx |
| 关键词 | Three-dimensional Displays Solid Modeling Computational Modeling Image Reconstruction Shape Geometry Vegetation |
| DOI | 10.1109/TVCG.2018.2869784 |
| 英文摘要 | In this paper, we describe a novel procedural modeling technique for generating realistic plant models from multi-view photographs. The realism is enhanced via visual and spatial information acquired from images. In contrast to previous approaches that heavily rely on user interaction to segment plants or recover branches in images, our method automatically estimates an accurate depth map of each image and extracts a 3D dense point cloud by exploiting an efficient stereophotogrammetry approach. Taking this point cloud as a soft constraint, we fit a parametric plant representation to simulate the plant growth progress. In this way, we are able to combine real data (photos and 3D point clouds) analysis with rule-based procedural plant modeling. We demonstrate the robustness of the proposed approach by modeling a variety of plants with complex branching structures and significant self-occlusions. We also demonstrate that the proposed framework can be used to reconstruct ground-covering plants, such as bushes and shrubs which have gained little attention in the literature. The effectiveness of our approach is validated by visually and quantitatively comparing with the state-of-the-art approaches.; In this paper, we describe a novel procedural modeling technique for generating realistic plant models from multi-view photographs. The realism is enhanced via visual and spatial information acquired from images. In contrast to previous approaches that heavily rely on user interaction to segment plants or recover branches in images, our method automatically estimates an accurate depth map of each image and extracts a 3D dense point cloud by exploiting an efficient stereophotogrammetry approach. Taking this point cloud as a soft constraint, we fit a parametric plant representation to simulate the plant growth progress. In this way, we are able to combine real data (photos and 3D point clouds) analysis with rule-based procedural plant modeling. We demonstrate the robustness of the proposed approach by modeling a variety of plants with complex branching structures and significant self-occlusions. We also demonstrate that the proposed framework can be used to reconstruct ground-covering plants, such as bushes and shrubs which have gained little attention in the literature. The effectiveness of our approach is validated by visually and quantitatively comparing with the state-of-the-art approaches. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/21686]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
| 通讯作者 | Dong-Ming Yan |
| 推荐引用方式 GB/T 7714 | Jianwei Guo,Shibiao Xu,Dong-Ming Yan,et al. Realistic Procedural Plant Modeling from Multiple View Images[J]. IEEE Transactions on Visualization and Computer Graphics,2018,xx(xx):xx. |
| APA | Jianwei Guo,Shibiao Xu,Dong-Ming Yan,Zhanglin Cheng,Marc Jaeger,&Xiaopeng Zhang.(2018).Realistic Procedural Plant Modeling from Multiple View Images.IEEE Transactions on Visualization and Computer Graphics,xx(xx),xx. |
| MLA | Jianwei Guo,et al."Realistic Procedural Plant Modeling from Multiple View Images".IEEE Transactions on Visualization and Computer Graphics xx.xx(2018):xx. |
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。