MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions.

Zhenpei Yang Zhile Ren Qi Shan Qixing Huang

Published in: CoRR (2021)

Keyphrases

multi view stereo
multi view
least squares
depth map
camera parameters
computationally intensive
three dimensional
object recognition
ground truth
surface reconstruction