能量引导流匹配

摘要

像素空间生成模型绕过了有损潜在压缩，但需要在高维空间中联合学习全局结构与细粒度细节。标准流匹配将噪声向固定的干净图像端点插值，使谱演化只能隐式学习。本文引入能量引导流匹配（Energy-Guided Flow Matching，EG-FM），通过移动端点显式建模由粗到细的生成轨迹。具体而言，EG-FM 用热核滤波端点替代固定端点，该端点从低频图像平滑演化至干净图像。移动端点中高频信号的比例由图像特定的能量引导调度释放，从而重新定向流匹配中的速度。我们的框架无需修改主干网络和训练数据，在训练和推理阶段仅引入可忽略的额外成本。实验中，EG-FM 在 ImageNet 类别条件图像生成任务 256×256 分辨率设置下以更少的训练轮次一致取得更低的 FID，在 200 轮时达到 FID 1.55，600 轮时达到 1.45。我们继续在 512×512 分辨率设置下训练生成任务，仅经过 40 轮高分辨率适配训练即取得 FID 1.58。此外，我们将 EG-FM 迁移至文本到图像生成任务，在 GenEval 上取得 0.85 分，在 DPG-Bench 上取得 83.9 分。代码见 https://github.com/ysng123/EG-FM。

English

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly. In this paper, we introduce Energy-Guided Flow Matching(EG-FM) that explicitly models a coarse-to-fine generative trajectory by moving endpoint. Specifically, EG-FM replaces the fixed endpoint with a heat-kernel-filtered endpoint that evolves smoothly from low-frequency image to clean image. The fraction of high-frequency signal in moving endpoint is released by an image-specific energy-guided scheduling, leading to the re-targeting of velocity in flow matching. Our framework requires no adaptation of the backbone and training data, bringing negligible cost on the training and inference stages. In our experiment, EG-FM consistently achieves lower FID on the ImageNet class-conditional image generation task at 256 times 256 with fewer epochs, reaching an FID of 1.55 at 200 epochs and 1.45 at 600 epochs. We continue training the generation task on the setting of 512 times 512 resolution, yielding a FID of 1.58 after only 40 high-resolution adaptation epochs. Furthermore, we transfer EG-FM on text-to-image generation and achieve 0.85 on GenEval score and 83.9 on DPG-Bench. Code is available at https://github.com/ysng123/EG-FM.