MIMFlow：结合掩码图像建模与归一化流的端到端图像生成

摘要

归一化流（NFs）是强大的生成模型，能够进行精确的密度估计和采样。然而，其严格的逆变换特性常迫使模型将能力消耗在低层次的像素细节上，从而阻碍对高层语义结构的捕捉。尽管掩码图像建模（MIM）在表示学习领域表现卓越，但其与生成管线的集成仍大多呈模块化且彼此割裂。本文提出MIMFlow，一种统一的端到端框架，联合优化潜在语义、像素重建和生成流。通过采用VAE编码器从掩码图像中推断语义潜在变量，MIMFlow实现了生成任务的原则性解耦：归一化流专注于建模简化的低频语义流形，而专用解码器负责高频合成。该设计有效解决了NFs固有的容量瓶颈，使模型能够优先关注全局结构一致性而非冗余噪声。在ImageNet 256×256上的实验结果表明，MIMFlow-L达到了71.3%的线性探测精度和2.50的FID值。尽管仅使用128个标记（比标准模型少50%），其性能相比同等规模的NF基线仍提升了32.8%。我们的代码开源在https://github.com/MCG-NJU/MIMFlow。

English

Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its capacity on low-level pixel details, hindering the capture of high-level semantic structures. While Masked Image Modeling (MIM) has excelled in representation learning, its integration into generative pipelines has remained largely modular and disjointed. In this paper, we propose MIMFlow, a unified end-to-end framework that jointly optimizes latent semantics, pixel reconstruction, and generative flow. By employing a VAE encoder to infer semantic latent from masked images, MIMFlow achieves a principled decoupling of the generative task: the Normalizing Flow focuses on modeling a simplified, low-frequency semantic manifold, while a specialized decoder handles high-frequency synthesis. This design effectively resolves the inherent capacity bottleneck of NFs, allowing the model to prioritize global structural coherence over redundant noise. Empirical results on ImageNet 256times256 show that MIMFlow-L reaches 71.3\% linear probing accuracy and an FID of 2.50. Despite using only 128 tokens (50\% fewer than standard models), it yields a 32.8\% performance gain over similar-scale NF baselines. Our code is available at https://github.com/MCG-NJU/MIMFlow.