Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs.

Xingang Pan Bo Dai Ziwei Liu Chen Change Loy Ping Luo

Published in: ICLR (2021)

Keyphrases

single image
image features
image data
image analysis
image content
multiscale
input image
edge detection
image pixels
image representation
image retrieval
image classification
image segmentation
region of interest
test images
keypoints
three dimensional
image collections
pixel values
image regions
hough transform
spatial information
low level
template matching
computer vision
segmentation algorithm
high resolution
geometric constraints
gray value
synthesized images