基于三维模型的数据驱动场景理解Data-Driven Scene Understanding from 3D Models |
|
课程网址: | http://videolectures.net/bmvc2012_satkin_scene_understanding/ |
主讲教师: | Scott Satkin |
开课单位: | 卡内基梅隆大学 |
开课时间: | 2012-10-09 |
课程语种: | 英语 |
中文简介: | 在本文中,我们提出了一种数据驱动的方法,以利用3D模型的存储库来进行场景理解。我们将图像中看到的内容与大量3D模型相关联的能力使我们能够从这些模型中传输信息,从而对场景产生了丰富的了解。我们开发了一个框架,用于自动校准相机,从拍摄图像的角度渲染3D模型,以及计算每个3D模型与输入图像之间的相似度。我们在几何估计的背景下演示了这种数据驱动的方法,并展示了在场景中找到对象的身份和姿势的能力。此外,我们提出了带有注释场景几何形状的新数据集。这些数据使我们能够在3D而非图像平面中衡量算法的性能。 p> |
课程简介: | In this paper, we propose a data-driven approach to leverage repositories of 3D models for scene understanding. Our ability to relate what we see in an image to a large collection of 3D models allows us to transfer information from these models, creating a rich understanding of the scene. We develop a framework for auto-calibrating a camera, rendering 3D models from the viewpoint an image was taken, and computing a similarity measure between each 3D model and an input image. We demonstrate this data-driven approach in the context of geometry estimation and show the ability to find the identities and poses of object in a scene. Additionally, we present a new dataset with annotated scene geometry. This data allows us to measure the performance of our algorithm in 3D, rather than in the image plane. |
关 键 词: | 3D模型; 数据集; 算法衡量 |
课程来源: | 视频讲座网 |
数据采集: | 2021-03-25:zyk |
最后编审: | 2021-03-25:zyk |
阅读次数: | 59 |