图 书 馆
学习对象的可预测生成向量表示Learning a Predictable and Generative Vector Representation for Objects |
|
| 课程网址: | http://videolectures.net/eccv2016_girdhar_vector_representation/ |
| 主讲教师: | Rohit Girdhar |
| 开课单位: | 卡内基梅隆大学 |
| 开课时间: | 2016-10-24 |
| 课程语种: | 英语 |
| 中文简介: |  对象的好的向量表示是什么？我们认为它应该是 3D 生成的，因为它可以生成新的 3D 对象；以及可以从 2D 预测，因为它可以从 2D 图像中感知。我们提出了一种新的架构，称为 TL 嵌入网络，以学习具有这些属性的嵌入空间。该网络由两个部分组成：（a）一个自动编码器，确保表示是生成的； (b) 一个卷积网络，确保表示是可预测的。这可以处理许多任务，包括从 2D 图像和 3D 模型检索进行体素预测。大量的实验分析证明了这种嵌入的有用性和多功能性。 |
| 课程简介: | What is a good vector representation of an object? We believe that it should be generative in 3D, in the sense that it can produce new 3D objects; as well as be predictable from 2D, in the sense that it can be perceived from 2D images. We propose a novel architecture, called the TL-embedding network, to learn an embedding space with these properties. The network consists of two components: (a) an autoencoder that ensures the representation is generative; and (b) a convolutional network that ensures the representation is predictable. This enables tackling a number of tasks including voxel prediction from 2D images and 3D model retrieval. Extensive experimental analysis demonstrates the usefulness and versatility of this embedding. |
| 关 键 词: | 自动编码器; 卷积网络; 3D 模型检索 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-06-23：zyk |
| 最后编审: | 2021-06-23：zyk |
| 阅读次数: | 56 |