SILO solves inverse problems with latent diffusion models by replacing pixel-space consistency with a learned latent degradation operator, cutting runtime and improving perceptual metrics at the cost of pixel fidelity.
Chan, Xiran Wang, and Omar A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SILO: Solving Inverse Problems with Latent Operators
SILO solves inverse problems with latent diffusion models by replacing pixel-space consistency with a learned latent degradation operator, cutting runtime and improving perceptual metrics at the cost of pixel fidelity.