XDGAN: Multi-Modal 3D Shape Generation in 2D Space.

Hassan Abu Alhaija Alara Dirik André Knörig Sanja Fidler Maria Shugrina

Published in: BMVC (2022)

Keyphrases

multi modal
multi modality
cross modal
image annotation
audio visual
three dimensional
high dimensional
video search
semantic concepts
information theoretic
multiple modalities
high level
feature extraction
vector space
uni modal