NullFlow: One-Step Generative Reconstruction
This work addresses the computational bottleneck of iterative generative reconstruction for image inpainting, offering a drastic speedup.
NullFlow achieves one-step generative image reconstruction by confining the flow to a measurement-consistent subspace, matching state-of-the-art diffusion solvers on image inpainting while reducing inference from hundreds of network evaluations to one.
We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measurement-consistent subspace. Because the flow never leaves this subspace, NullFlow needs no separate data-fidelity corrections, unlike existing solvers. NullFlow samples in a single network evaluation by learning the flow's average velocity, avoiding the step-by-step integration of traditional flow matching methods. We prove that the average velocity of this constrained flow yields a training objective whose global minimizer is a one-step posterior sampler. We show on image inpainting that NullFlow matches state-of-the-art diffusion solvers while cutting inference from hundreds of network evaluations to one.