直接流向现实：用于高效图像复原的感知一致流匹配
Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration
浏览论文内容
中文总结 AI 辅助
本文提出PCFlow框架，通过结合潜在一致性流目标、LCPL损失与无冲突梯度投影策略，实现高效图像复原，在低计算成本下取得竞争力性能。
中文摘要 AI 辅助
图像复原本质上受限于失真与感知之间的权衡：最小化像素级误差会产生过度平滑的结果，而优化感知真实性往往会引入结构偏差。近期方法尝试通过后验采样或多阶段生成流水线平衡这一权衡，但仍存在计算成本高、架构复杂的问题。为克服这些局限，我们提出PCFlow（Perceptually Consistent Flow Matching，感知一致流匹配），这是一个将退化观测直接参数化为到干净目标的连续迁移的统一框架，联合优化失真与感知质量。其潜在一致性流目标驱动稳定高效的少步推理，而潜在一致性感知损失（Latent Consistency Perceptual Loss，LCPL）直接对引导速度场施加语义约束，引导动力学朝向视觉锐利的数据流形。此外，考虑到结构一致性与感知一致性之间的固有冲突，我们整合无冲突梯度投影策略以稳定多目标优化景观。结合仅含卷积的轻量骨干网络，PCFlow在各类复原任务上实现了有竞争力的性能，且计算成本仅为传统方法的一小部分。
英文摘要
Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations. Recent approaches attempt to balance this tradeoff via posterior sampling or multi-stage generative pipelines, yet remain computationally expensive and architecturally complex. To overcome these limitations, we propose PCFlow (Perceptually Consistent Flow Matching), a unified framework that directly parameterizes a continuous transport from degraded observations to clean targets, jointly optimizing distortion and perceptual quality. While its latent consistency flow objective drives stable and efficient few-step inference, a Latent Consistency Perceptual Loss (LCPL) imposes semantic constraints directly on the guiding velocity field, steering the dynamics toward visually sharp data manifolds. Furthermore, recognizing the inherent conflict between structural and perceptual consistencies, we integrate a conflict-free gradient projection strategy to stabilize the multi-objective optimization landscape. Combined with lightweight, convolution-only backbone, PCFlow achieves competitive performance across diverse restoration tasks at a fraction of traditional computational costs.
发表机构
- Korea University（高丽大学）
- Aim Future
机构由 AI 辅助整理，请以论文原文为准。
