P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting.

Ziyi Wang Xumin Yu Yongming Rao Jie Zhou Jiwen Lu

Published in: NeurIPS (2022)

Keyphrases

human body
pre trained
point cloud
input image
pixel level
three dimensional
single image
structure from motion
machine learning
decision trees
similarity measure
viewpoint
high resolution
hough transform
image matching