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: CoRR (2022)

Keyphrases

pre trained
point cloud
input image
image segmentation
structure from motion
single image
pixel level
training data
high resolution
point sets
image set