Image Generation on NLST (test)
0.202LPIPSCorrFlowNet (ODE)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| CorrFlowNet (ODE)Method category=Deterministic Methods, Sampling algorithm=ODE2026.03 | 0.202 | 91.695 | |
| CorrFlowNet (SDE)Method category=Stochastic Methods, Sampling algorithm=SDE, Number of stochastic samples=202026.03 | 0.202 | 88.56 | |
| NAMD (w/o Lalign)Method category=Stochastic Methods, Ablation=without alignment loss L_align, Number of stochastic samples=202026.03 | 0.205 | 101.301 | |
| SD1.5Method category=Stochastic Methods, Number of stochastic samples=202026.03 | 0.207 | 97.55 | |
| NAMD (Ours)Method category=Stochastic Methods, Number of stochastic samples=202026.03 | 0.22 | 83.06 | |
| DDL-CXRMethod category=Stochastic Methods, Number of stochastic samples=202026.03 | 0.235 | 122.41 | |
| Flux (Rectified Flow)Method category=Stochastic Methods, Sampling algorithm=Rectified Flow, Number of stochastic samples=202026.03 | 0.248 | 95.843 | |
| ImageFlowNet (SDE)Method category=Stochastic Methods, Sampling algorithm=SDE, Number of stochastic samples=202026.03 | 0.362 | 217.706 | |
| McWGANMethod category=Deterministic Methods2026.03 | 0.364 | 80.443 |