BriefGPT.xyz
Jul, 2021
从图像集合中发现三维部件
Discovering 3D Parts from Image Collections
HTML
PDF
Chun-Han Yao, Wei-Chih Hung, Varun Jampani, Ming-Hsuan Yang
TL;DR
本文提出了一种自我监督的方法(LPD)来发现只有2D图像的物体的三维部件,并使用新的部件形状先验学习足够简单而又能忠实地匹配物体形状的部件,这种方法在实验中表现良好,比现有方法具有更好的重构精度。
Abstract
Reasoning
3d shapes
from
2d images
is an essential yet challenging task, especially when only single-view images are at our disposal. While an object can have a complicated shape, individual parts are usually clo
→