PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation.

Shaolin Zhu Shangjie Li Yikun Lei Deyi Xiong

Published in: ACL (1) (2023)

Keyphrases

end to end
pre trained
image features
training data
multiscale
training examples
multi modal
input image
probabilistic model
single image
parametric models
small number
feature points
high resolution
statistical model
image retrieval
congestion control
image matching
feature space