Abstract
There is some ambiguity in the 3D shape of an object
when the number of observed views is small. Because of
this ambiguity, although a 3D object reconstructor can be
trained using a single view or a few views per object, reconstructed shapes only fit the observed views and appear
incorrect from the unobserved viewpoints. To reconstruct
shapes that look reasonable from any viewpoint, we propose
to train a discriminator that learns prior knowledge regarding possible views. The discriminator is trained to distinguish the reconstructed views of the observed viewpoints
from those of the unobserved viewpoints. The reconstructor
is trained to correct unobserved views by fooling the discriminator. Our method outperforms current state-of-theart methods on both synthetic and natural image datasets;
this validates the effectiveness of our method