图 书 馆
在跳扩散混合的多视图重建Hybrid Multi-view Reconstruction by Jump-Diffusion |
|
| 课程网址: | http://videolectures.net/cvpr2010_lafarge_hmvr/ |
| 主讲教师: | Florent Lafarge |
| 开课单位: | 法国国家信息与自动化研究所 |
| 开课时间: | 2010-07-19 |
| 课程语种: | 英语 |
| 中文简介: | 我们提出了一种多视图立体重建算法，它将城市场景恢复为网格和几何图元的组合。它提供了一个紧凑的模型，同时保留了细节：不规则元素，如雕像和装饰物由网格描述，而常规结构，如列和墙壁由基元（平面，球体，圆柱，圆锥体和圆环）描述。跳跃扩散过程旨在同时对这两种类型的元素进行采样。通过多物体能量模型来测量重建的质量，该模型考虑了光学一致性和语义考虑（即几何形状和形状布局）。采样器嵌入到迭代细化过程中，该过程提供越来越精确的混合表示。给出了复杂城市结构和大场景的实验结果，并与基于多视图的网格划分算法进行了比较。 |
| 课程简介: | We propose a multi-view stereo reconstruction algorithm which recovers urban scenes as a combination of meshes and geometric primitives. It provides a compact model while preserving details: irregular elements such as statues and ornaments are described by meshes whereas regular structures such as columns and walls are described by primitives (planes, spheres, cylinders, cones and tori). A Jump- Diffusion process is designed to sample these two types of elements simultaneously. The quality of a reconstruction is measured by a multi-object energy model which takes into account both photo-consistency and semantic considerations (i.e. geometry and shape layout). The sampler is embedded into an iterative refinement procedure which provides an increasingly accurate hybrid representation. Experimental results on complex urban structures and large scenes are presented and compared to multi-view based meshing algorithms. |
| 关 键 词: | 多视点立体重构算法; 网格化算法; 城市景观 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-07-17：yumf |
| 阅读次数: | 43 |