Self-supervised generative learning using noisy measurements and equivariant imaging constraints
Adversarial training with measurement consistency achieves lowest generation MSE (2.96) by implicitly regularizing the nullspace.
Langevin-based diffusion proxy achieves MSE 2.72 through iterative measurement-guided denoising.
Measurement-space ELBO does not constrain the nullspace, leading to higher MSE (5.81) and potential mode collapse.
Quality degrades sharply beyond condition number 50, establishing practical feasibility limits.