A two-step wrapper (invert candidate to latent, then run DPS from that latent) improves hard inpainting results, with mixed or negative superresolution results and toy-model theory.
Inverse optimization: Theory and applications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
A two-step wrapper (invert candidate to latent, then run DPS from that latent) improves hard inpainting results, with mixed or negative superresolution results and toy-model theory.