用于少步生成建模的感知流匹配
Perceptual Flow Matching for Few-Step Generative Modeling
AI总结：
提出感知流匹配框架，在感知特征空间监督流匹配，改进少步生成能力，减少采样步骤，无需教师模型和辅助分数网络，实验表明其能产生高质量结果。
摘要：
我们提出了感知流匹配（PFM），这是一种用于流匹配模型中少步生成的简单而有效的框架。与在传统VAE潜在空间中执行速度回归不同，PFM使用预训练的感知模型在感知特征空间中监督流匹配。这一简单变化显著提高了流匹配模型的少步生成能力，在保持生成质量的同时将采样步骤从35 - 50减少到4 - 8。与现有加速和蒸馏方法不同，PFM既不需要教师模型也不需要辅助分数网络，并且可以通过最小的修改集成到标准流匹配训练管道中。在图像生成、视频生成和图像编辑任务上的大量实验表明，PFM始终能产生高质量的结果，同时比现有的基于蒸馏的方法产生更少的伪像。我们进一步表明，感知监督将回归最小化器从均值寻求转变为模式寻求，使预测偏向于在粗略少步积分下仍然准确的流形模式。我们的结果表明，当在适当的表示空间中进行监督时，标准流匹配训练可以自然地产生高质量的少步生成器。我们希望这一见解能激发未来对用于高效生成建模的表示感知目标的研究。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
