Perceptual Flow Matching for Few-Step Generative Modeling

• URL: http://arxiv.org/abs/2607.03524v1
• Date: Fri, 03 Jul 2026 17:55:01 GMT
• Title: Perceptual Flow Matching for Few-Step Generative Modeling
• Abstract summary: Perceptual Flow Matching is a framework for few-step generation in flow-matching models.<n>We show that PFM produces high-quality few-step generators when supervised in an appropriate representation space.
• Score: 64.26537634881244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose Perceptual Flow Matching (PFM), a simple yet effective framework for few-step generation in flow-matching models. Rather than performing velocity regression in the conventional VAE latent space, PFM supervises flow matching in a perceptual feature space using pretrained perceptual models. This simple change substantially improves the few-step generation capability of flow-matching models, reducing the number of sampling steps from 35-50 to 4-8 while preserving generation quality. Unlike existing acceleration and distillation approaches, PFM requires neither teacher models nor auxiliary score networks and can be integrated into standard flow-matching training pipelines with minimal modifications. Extensive experiments on image generation, video generation, and image editing tasks demonstrate that PFM consistently produces high-quality results while producing fewer artifacts than existing distillation-based methods. We further show that perceptual supervision shifts the regression minimizer from mean-seeking to mode-seeking, biasing predictions toward on-manifold modes that remain accurate under coarse few-step integration. Our results reveal that standard flow-matching training can naturally yield high-quality few-step generators when supervised in an appropriate representation space. We hope this insight inspires future research into representation-aware objectives for efficient generative modeling.

Related papers

• Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning [8.422673935994451]
  consistency distillation has significantly accelerated the inference of diffusion models.<n>We propose Curvature-Adaptive Consistency Flow Matching to address the limitations of static sampling.<n>Our approach achieves new state-of-the-art results on large-scale models such as FLUX and SDXL.
  arXiv  Detail & Related papers  (2026-06-21T08:49:50Z)
• Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models [34.59515048908997]
  Mean Flow Distillation (MFD) is a novel distillation framework tailored for flow matching models.<n>MFD acts as a temporal low-pass filter, effectively suppressing the high-frequency optimization noise.<n>We prove the Mean Flow Matching Theorem, establishing that matching expected average velocities is sufficient for strict distribution alignment.
  arXiv  Detail & Related papers  (2026-06-09T17:39:19Z)
• Drift Flow Matching [69.16550765154163]
  We propose Drift Flow Matching, a framework that connects drifting generative modeling with flow-based iterative generation.<n>DFM preserves the efficiency of direct transport maps while enabling generation to be refined through multiple inference steps.
  arXiv  Detail & Related papers  (2026-05-17T03:58:01Z)
• Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems [3.692960109077297]
  We study whether a high-fidelity flow-matching generative model can be compressed into a compact one-step model for fast scientific flow reconstruction.<n>Our approach distills an optimal-transport flow-matching teacher into a one-step consistency model.<n>Low-fidelity observations are incorporated at inference by initializing the generative trajectory from a noised observation along the transport path.
  arXiv  Detail & Related papers  (2026-05-07T10:20:50Z)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• A-FloPS: Accelerating Diffusion Sampling with Adaptive Flow Path Sampler [21.134678093577193]
  A-FloPS is a principled, training-free framework for flow-based generative models.<n>We show that A-FloPS consistently outperforms state-of-the-art training-free samplers in both sample quality and efficiency.<n>With as few as $5$ function evaluations, A-FloPS achieves substantially lower FID and generates sharper, more coherent images.
  arXiv  Detail & Related papers  (2025-08-22T13:28:16Z)
• Align Your Flow: Scaling Continuous-Time Flow Map Distillation [63.927438959502226]
  Flow maps connect any two noise levels in a single step and remain effective across all step counts.<n>We extensively validate our flow map models, called Align Your Flow, on challenging image generation benchmarks.<n>We show text-to-image flow map models that outperform all existing non-adversarially trained few-step samplers in text-conditioned synthesis.
  arXiv  Detail & Related papers  (2025-06-17T15:06:07Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• PFCM: Poisson flow consistency models for low-dose CT image denoising [3.3153763098433258]
  We introduce PFCM, a novel family of deep generative models that combines the robustness of PFGM++ with the efficient single-step sampling of consistency models.<n>We exploit to adapt PFCM for the task of low-dose CT image denoising, via a task-specific'' sampler that hijacks'' the generative process.<n>The resulting sampler achieves excellent performance in terms of LPIPS, SSIM, and PSNR on the Mayo low-dose CT dataset.
  arXiv  Detail & Related papers  (2024-02-13T01:39:56Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.