NORB

NORB Dataset是用于基于形状的3D对象重新定位的实验数据集，其中包含5个通用类别的四足动物，人，飞机，卡车和汽车中的50个玩具图像。数据集中的对象由两个摄像机在6个光照条件、9个高度和18个方位角下成像，由5个实例的训练集和5个实例的测试集组成。
该数据集由纽约大学2004年发布，主要出版商为黄傅杰和Yann LeCun，相关论文包括《姿势和灯光不变性的通用对象识别的学习方法》。

The NORB Dataset is an experimental dataset for shape-based 3D object relocalization. It contains 50 toy images across 5 general categories: quadrupeds, humans, airplanes, trucks, and cars. The objects in the dataset were captured by two cameras under 6 lighting conditions, 9 elevation angles, and 18 azimuth angles. It is divided into a training set with 5 instances and a test set with 5 instances.
This dataset was released by New York University in 2004, with its primary publishers being Fu Jie Huang and Yann LeCun. The associated paper is titled *Learning Methods for Generic Object Recognition with Pose and Lighting Invariance*.

搜集汇总

背景与挑战

背景概述

NORB数据集是一个用于3D对象重新定位的实验数据集，包含5个类别的玩具图像，由纽约大学2004年发布。数据集中的对象在两个摄像机、不同光照条件和角度下成像，适用于基于形状的对象识别研究。