One-Step Face Restoration via Shortcut-Enhanced Coupling Flow
This work addresses the problem of efficient and high-quality face restoration for applications where speed and accuracy are crucial, such as video conferencing or image editing, providing an incremental improvement over existing methods.
The authors tackled the problem of face restoration, achieving state-of-the-art one-step restoration quality with SCFlowFR, while maintaining inference speed comparable to traditional non-diffusion methods. This approach results in improved face restoration quality.
Face restoration has advanced significantly with generative models like diffusion models and flow matching (FM), which learn continuous-time mappings between distributions. However, existing FM-based approaches often start from Gaussian noise, ignoring the inherent dependency between low-quality (LQ) and high-quality (HQ) data, resulting in path crossovers, curved trajectories, and multi-step sampling requirements. To address these issues, we propose Shortcut-enhanced Coupling flow for Face Restoration (SCFlowFR). First, it establishes a \textit{data-dependent coupling} that explicitly models the LQ--HQ dependency, minimizing path crossovers and promoting near-linear transport. Second, we employ conditional mean estimation to obtain a coarse prediction that refines the source anchor to tighten coupling and conditions the velocity field to stabilize large-step updates. Third, a shortcut constraint supervises average velocities over arbitrary time intervals, enabling accurate one-step inference. Experiments demonstrate that SCFlowFR achieves state-of-the-art one-step face restoration quality with inference speed comparable to traditional non-diffusion methods.