Search papers, labs, and topics across Lattice.
DVFace, a one-step diffusion framework, is introduced for video face restoration, addressing limitations of existing multi-step diffusion approaches in facial adaptation and inference efficiency. The framework employs a spatio-temporal dual-codebook to extract spatial and temporal facial priors and an asymmetric fusion module to inject these priors into the diffusion backbone. Experiments demonstrate that DVFace achieves superior restoration quality, temporal consistency, and identity preservation on benchmark datasets.
One-step diffusion for video face restoration is now viable, achieving state-of-the-art results by learning separate spatial and temporal priors.
Video face restoration aims to enhance degraded face videos into high-quality results with realistic facial details, stable identity, and temporal coherence. Recent diffusion-based methods have brought strong generative priors to restoration and enabled more realistic detail synthesis. However, existing approaches for face videos still rely heavily on generic diffusion priors and multi-step sampling, which limit both facial adaptation and inference efficiency. These limitations motivate the use of one-step diffusion for video face restoration, yet achieving faithful facial recovery alongside temporally stable outputs remains challenging. In this paper, we propose, DVFace, a one-step diffusion framework for real-world video face restoration. Specifically, we introduce a spatio-temporal dual-codebook design to extract complementary spatial and temporal facial priors from degraded videos. We further propose an asymmetric spatio-temporal fusion module to inject these priors into the diffusion backbone according to their distinct roles. Evaluation on various benchmarks shows that DVFace delivers superior restoration quality, temporal consistency, and identity preservation compared to recent methods. Code: https://github.com/zhengchen1999/DVFace.
