BDBM uses a single masked noise-prediction network to model both forward and backward diffusion bridges between two image distributions, enabling bidirectional translation at roughly half the model cost.
Pattern recognition and machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Bidirectional Diffusion Bridge Models
BDBM uses a single masked noise-prediction network to model both forward and backward diffusion bridges between two image distributions, enabling bidirectional translation at roughly half the model cost.