HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
Diffusion posterior sampling for general noisy inverse problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Diffusion priors for sparse-view CT work on synthetic data but face domain shift and forward model mismatch on experimental phantom data, with annealed likelihood weights offering partial mitigation.
citing papers explorer
-
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
-
Towards reconstructing experimental sparse-view X-ray CT data with diffusion models
Diffusion priors for sparse-view CT work on synthetic data but face domain shift and forward model mismatch on experimental phantom data, with annealed likelihood weights offering partial mitigation.