用混合高斯建模流速，6步生成高质量图像。
Gaussian Mixture Flow Matching Models
- 用动态高斯混合模型预测多模态流速，替代传统单高斯均值。
- 6步采样在ImageNet上达到0.942精度，优于现有流匹配方法。
- 新指导机制缓解颜色过饱和，适合高保真图像生成场景。
扩散模型将去噪分布近似为高斯并预测其均值，而流匹配模型将高斯均值重参数化为流速度。然而，它们在少步采样中因离散化误差表现不佳，且在无分类器指导（CFG）下易产生过饱和色彩。为此，我们提出新型高斯混合流匹配（GMFlow）模型：不再预测均值，而是预测动态高斯混合（GM）参数以捕捉多模态流速度分布，可通过KL散度损失学习。我们证明，GMFlow统一了此前的扩散与流匹配模型（前者以$ L_2 $去噪损失学习单高斯）。推理时，我们推导出基于解析去噪分布和速度场的GM-SDE/ODE求解器，实现精准少步采样。此外，引入新颖的概率引导方案，缓解CFG导致的颜色过饱和问题，提升图像质量。大量实验表明，GMFlow在生成质量上持续超越流匹配基线，在ImageNet 256×256上仅用6步采样即达0.942精度。
原文摘要 · Abstract (English)
Diffusion models approximate the denoising distribution as a Gaussian and predict its mean, whereas flow matching models reparameterize the Gaussian mean as flow velocity. However, they underperform in few-step sampling due to discretization error and tend to produce over-saturated colors under classifier-free guidance (CFG). To address these limitations, we propose a novel Gaussian mixture flow matching (GMFlow) model: instead of predicting the mean, GMFlow predicts dynamic Gaussian mixture (GM) parameters to capture a multi-modal flow velocity distribution, which can be learned with a KL divergence loss. We demonstrate that GMFlow generalizes previous diffusion and flow matching models where a single Gaussian is learned with an $L_2$ denoising loss. For inference, we derive GM-SDE/ODE solvers that leverage analytic denoising distributions and velocity fields for precise few-step sampling. Furthermore, we introduce a novel probabilistic guidance scheme that mitigates the over-saturation issues of CFG and improves image generation quality. Extensive experiments demonstrate that GMFlow consistently outperforms flow matching baselines in generation quality, achieving a Precision of 0.942 with only 6 sampling steps on ImageNet 256$\times$256.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。