One Thing One Click++: Self-Training for Weakly Supervised 3D Scene Understanding.

Zhengzhe Liu Xiaojuan Qi Chi-Wing Fu

Published in: CoRR (2023)

Keyphrases

d scene
weakly supervised
semi supervised
single image
topic models
depth map
superpixels
object class
relation extraction
optical flow
high quality
machine learning
learning algorithm
image segmentation
object recognition
training set
computer vision