📝 SummarXiv

Abstract

Video Face Enhancement (VFE) seeks to reconstruct high-quality facial regions from degraded video sequences, a capability that underpins numerous applications including video conferencing, film restoration, and surveillance. Despite substantial progress in the field, current methods that primarily rely on video super-resolution and generative frameworks continue to face three fundamental challenges: (1) faithfully modeling intricate facial textures while preserving temporal consistency; (2) restricted model generalization due to the lack of high-quality face video training data; and (3) low efficiency caused by repeated denoising steps during inference. To address these challenges, we propose VividFace, a novel and efficient one-step diffusion framework for video face enhancement. Built upon the pretrained WANX video generation model, our method leverages powerful spatiotemporal priors through a single-step flow matching paradigm, enabling direct mapping from degraded inputs to high-quality outputs with significantly reduced inference time. To further boost efficiency, we propose a Joint Latent-Pixel Face-Focused Training strategy that employs stochastic switching between facial region optimization and global reconstruction, providing explicit supervision in both latent and pixel spaces through a progressive two-stage training process. Additionally, we introduce an MLLM-driven data curation pipeline for automated selection of high-quality video face datasets, enhancing model generalization. Extensive experiments demonstrate that VividFace achieves state-of-the-art results in perceptual quality, identity preservation, and temporal stability, while offering practical resources for the research community.