PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.
Generative plug and play: Posterior sampling for inverse problems.arXiv preprint arXiv:2306.07233,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unbiased Diffusion Variational Inversion via Principled Posterior Matching
PPM derives a tractable gradient for exact KL optimization in diffusion variational inversion to achieve unbiased posterior matching without heuristic approximations.