TearingNet: Point Cloud Autoencoder To Learn Topology-Friendly Representations.

Jiahao Pang Duanshun Li Dong Tian

Published in: CVPR (2021)

Keyphrases

point cloud
structure from motion
surface reconstruction
implicit surfaces
point cloud data
point sets
stereo camera
triangular mesh
normal vectors
laser scanner
nearest neighbor
stereo vision
real world objects
lidar data
machine learning
feature vectors
object recognition
image sequences
three dimensional