RGFVR: Reference-Guided Face Video Restoration with Flow Matching
It addresses identity preservation in face video restoration for general users without subject-specific training, but the method is incremental as it adapts existing flow-based models.
The paper proposes a reference-guided face video restoration framework that uses bimodal identity conditioning in a flow-based generator, achieving improved fidelity, temporal consistency, and identity preservation under various degradations.
Face video restoration from degraded observations is challenging, as it requires simultaneously recovering visual fidelity, temporal consistency, and subject identity. Existing approaches are often either reference-free, which can lead to identity loss when person-specific facial details are lost, or subject-specific, which limits generalization to unseen identities. We propose a subject-agnostic, reference-guided framework for identity-preserving face video restoration. Our method introduces bimodal perceptual-descriptive identity conditioning into a pretrained flow-based text-to-video generator and employs a two-stage training strategy to strengthen identity guidance during restoration. Experiments show that our approach improves restoration fidelity, temporal consistency, and identity preservation, achieving superior performance under challenging video degradations, including downsampling, blur, noise, and compression artifacts. The code is available under: https://github.com/batuhanntosun/RG-FVR.