English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Face video restoration (FVR) is a challenging but important problem where oneseeks to recover a perceptually realistic face videos from a low-quality input.While diffusion probabilistic models (DPMs) have been shown to achieveremarkable performance for face image restoration, they often fail to preservetemporally coherent, high-quality videos, compromising the fidelity ofreconstructed faces. We present a new conditional diffusion framework calledFLAIR for FVR. FLAIR ensures temporal consistency across frames in acomputationally efficient fashion by converting a traditional image DPM into avideo DPM. The proposed conversion uses a recurrent video refinement layer anda temporal self-attention at different scales. FLAIR also uses a conditionaliterative refinement process to balance the perceptual and distortion qualityduring inference. This process consists of two key components: adata-consistency module that analytically ensures that the generated videoprecisely matches its degraded observation and a coarse-to-fine imageenhancement module specifically for facial regions. Our extensive experimentsshow superiority of FLAIR over the current state-of-the-art (SOTA) for videosuper-resolution, deblurring, JPEG restoration, and space-time frameinterpolation on two high-quality face video datasets.

FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restoration