Rectified MeanFlow: Overcoming the Curvature Bottleneck in MeanFlow

Flow-based models are powerful generators, but sampling typically requires costly numerical integration along curved generative trajectories. MeanFlow offers a promising framework to few-step generation by directly learning mean-velocity fields. However, we find that the highly curved generative trajectories of existing models induce a noisy loss landscape, severely bottlenecking convergence and model quality. We leverage a fundamental geometric principle to overcome this: mean-velocity estimation is drastically simpler along straight paths. Building on this insight, we propose Rectified MeanFlow, a self-distillation approach that learns the mean-velocity field over a straightened velocity field, induced by rectified couplings from a pretrained model. By smoothing the optimization landscape, our method achieves strong few-step generation performance. Under the same pretrained initialization and matched end-to-end post-training budgets, including coupling generation, Re-MeanFlow reduces guided one-step FID from $7.48$ to $3.03$ on ImageNet-$512^2$. In a controlled text-to-image proof of concept using Cosmos-Predict2-2B, it improves GenEval from $0.6331$ to $0.7385$ at $4$ NFE, compared with approximately $0.80$ for the $70$-NFE teacher. Together, these results highlight the synergy between trajectory rectification and mean-velocity modelling as an effective route to compute-efficient few-step generation.