BriefGPT.xyz
Jun, 2024
ImageNet3D:面向通用对象级别3D理解
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
HTML
PDF
Wufei Ma, Guanning Zeng, Guofeng Zhang, Qihao Liu, Letian Zhang...
TL;DR
通过与ImageNet数据集相结合,ImageNet3D数据集提供了200个类别的2D和3D信息,从而为构建具有更强的通用性目标级三维理解的视觉模型提供了潜力。
Abstract
A
vision model
with general-purpose
object-level 3d understanding
should be capable of inferring both 2D (e.g., class name and bounding box) and 3D information (e.g., 3D location and 3D viewpoint) for arbitrary r
→