用邻居信息提升图像生成速度场，效果显著且成本低。
Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields
- 将速度场分解为反应项和邻域扩散项，引入局部上下文。
- 在5个数据集上平均提升FID和召回率，改善生成质量。
- 轻量级模块化设计，适配现有流匹配模型，计算开销小。
流匹配将样本生成建模为学习一个连续时间速度场，将噪声逐步转化为数据。现有流匹配网络通常独立预测每个点的速度，仅依赖其位置和时间，忽略邻近点信息。然而，这种逐点方法可能遗漏生成轨迹中点之间的相关性，影响速度预测精度。为此，我们提出图流匹配（GFM），通过图神经网络模块聚合邻域信息，将学习到的速度分解为反应项（任意标准流匹配网络）与扩散项。该反应-扩散框架在保持深度流模型可扩展性的同时，以极低额外开销丰富了速度预测的局部上下文。在预训练变分自编码器的潜在空间中运行，GFM在五个图像生成基准（LSUN Church、LSUN Bedroom、FFHQ、AFHQ-Cat 和 CelebA-HQ，分辨率 $256\times256$）上均一致提升了弗雷切特初始距离（FID）和召回率，验证了其作为现有流匹配架构的模块化增强的有效性。
原文摘要 · Abstract (English)
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time along its flow trajectory, and ignoring neighboring points. However, this pointwise approach may overlook correlations between points along the generation trajectory that could enhance velocity predictions, thereby improving downstream generation quality. To address this, we propose Graph Flow Matching (GFM), a lightweight enhancement that decomposes the learned velocity into a reaction term -- any standard flow matching network -- and a diffusion term that aggregates neighbor information via a graph neural module. This reaction-diffusion formulation retains the scalability of deep flow models while enriching velocity predictions with local context, all at minimal additional computational cost. Operating in the latent space of a pretrained variational autoencoder, GFM consistently improves Fréchet Inception Distance (FID) and recall across five image generation benchmarks (LSUN Church, LSUN Bedroom, FFHQ, AFHQ-Cat, and CelebA-HQ at $256\times256$), demonstrating its effectiveness as a modular enhancement to existing flow matching architectures.
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。