通过显式建模低质与高质图像关联，实现人脸修复的一步快速重建。
Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
- 基于数据依赖的耦合流，显式建模低质与高质图像关系
- 单步推理下实现最优感知保真度与计算效率平衡
- 引入捷径约束稳定大步长更新，减少离散化误差
人脸修复可被建模为通过流匹配（Flow Matching, FM）在图像分布间进行连续时间变换。然而，标准FM通常采用独立耦合，忽略了低质量（LQ）与高质量（HQ）数据间的统计相关性，导致轨迹交叉和速度场曲率高，需多步积分。本文提出面向人脸修复的捷径约束耦合流（SCFlowFR），通过建立数据依赖的耦合方式，显式建模LQ-HQ依赖关系，最小化路径交叉并促进近线性概率流。此外，采用条件均值估计器优化源分布锚点，有效降低传输成本并稳定速度场。为确保单步推断稳定，引入捷径约束以监督任意区间上的平均速度，缓解大步长更新中的离散化偏差。SCFlowFR在单步恢复中达到当前最优性能，实现了感知保真度与计算效率的优越权衡。
原文摘要 · Abstract (English)
Face restoration can be formulated as a continuous-time transformation between image distributions via Flow Matching (FM). However, standard FM typically employs independent coupling, ignoring the statistical correlation between low-quality (LQ) and high-quality (HQ) data. This leads to intersecting trajectories and high velocity-field curvature, requiring multi-step integration. We propose Shortcut-constrained Coupling Flow for Face Restoration (SCFlowFR) to address these challenges. By establishing a data-dependent coupling, we explicitly model the LQ-HQ dependency to minimize path crossovers and promote near-linear probability flow. Furthermore, we employ a conditional mean estimator to refine the source distribution's anchor, effectively tightening the transport cost and stabilizing the velocity field. To ensure stable one-step inference, a shortcut constraint is introduced to supervise average velocities over arbitrary intervals, mitigating discretization bias in large-step updates. SCFlowFR achieves state-of-the-art one-step restoration, providing a superior trade-off between perceptual fidelity and computational efficiency.
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。