Helmholtz Distillation plus Negative Caching amortizes Energy Matching to 3D CT volumes, producing a conservative prior that improves FID and sparse-view reconstruction over pure flow baselines.
Maximum likelihood training of score-based diffusion models , isbn =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Projected Energy Matching for Generative 3D Priors
Helmholtz Distillation plus Negative Caching amortizes Energy Matching to 3D CT volumes, producing a conservative prior that improves FID and sparse-view reconstruction over pure flow baselines.