Learning single-image 3D reconstruction by generative modelling of shape, pose and shading.

Paul Henderson Vittorio Ferrari

Published in: CoRR (2019)

Keyphrases

single image
shape recovery
d scene
multiple images
shape from shading
partially occluded
light source
image pairs
intrinsic images
computer vision
intrinsic image decomposition
super resolution
photometric stereo
surface normals
structured light
indoor scenes