Papers
arxiv:2501.09960

Discrete Prior-based Temporal-coherent Content Prediction for Blind Face Video Restoration

Published on Jan 17
Authors:
,
,
,
,
,
,
,

Abstract

The DP-TempCoh model restores high-fidelity face videos using a Discrete Prior-based Temporal-Coherent content prediction transformer, enhancing temporal coherence and stability in face attributes.

AI-generated summary

Blind face video restoration aims to restore high-fidelity details from videos subjected to complex and unknown degradations. This task poses a significant challenge of managing temporal heterogeneity while at the same time maintaining stable face attributes. In this paper, we introduce a Discrete Prior-based Temporal-Coherent content prediction transformer to address the challenge, and our model is referred to as DP-TempCoh. Specifically, we incorporate a spatial-temporal-aware content prediction module to synthesize high-quality content from discrete visual priors, conditioned on degraded video tokens. To further enhance the temporal coherence of the predicted content, a motion statistics modulation module is designed to adjust the content, based on discrete motion priors in terms of cross-frame mean and variance. As a result, the statistics of the predicted content can match with that of real videos over time. By performing extensive experiments, we verify the effectiveness of the design elements and demonstrate the superior performance of our DP-TempCoh in both synthetically and naturally degraded video restoration.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2501.09960 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2501.09960 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2501.09960 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.