AI Paper Atlas

Research map / 3D vision / Face and shape

Face Video Deblurring Using 3D Facial Priors

Wenqi Ren, Jiaolong Yang, Senyou Deng, David Wipf, Xiaochun Cao, Xin Tong

ICCV 2019 · 3D vision › Face and shape · approach: 3D morphable face model regression · 46 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the rendered 3D face as guidance (no identity vector) (ablation)Face video deblurring network · 300VW (9 synthetic test videos)PSNR: 36.74 -> 37.53Improved
add the rendered 3D face as guidance (no identity vector) (ablation)Face video deblurring network · 300VW (9 synthetic test videos)SSIM: 0.9817 -> 0.9869Improved
add the identity vector alone (no rendered face) (ablation)Face video deblurring network · 300VW (9 synthetic test videos)PSNR: 36.74 -> 36.82No clear effect
add the identity vector alone (no rendered face) (ablation)Face video deblurring network · 300VW (9 synthetic test videos)identity similarity: 0.8352 -> 0.8335Hurt
add the identity vector on top of the rendered face (ablation)Face video deblurring network · 300VW (9 synthetic test videos)PSNR: 37.53 -> 37.70Improved
add the identity vector on top of the rendered face (ablation)Face video deblurring network · 300VW (9 synthetic test videos)SSIM: 0.9869 -> 0.9849Hurt
add the identity vector on top of the rendered face (ablation)Face video deblurring network · 300VW (9 synthetic test videos)identity similarity: 0.8364 -> 0.8373Improved
use the proposed 3D-prior network instead of Su et al. video deblurring baselineFace video deblurring network · 300VW (9 synthetic test videos)PSNR: 34.40 -> 37.70Improved
use the proposed 3D-prior network instead of Su et al. on unseen dataFace video deblurring network · VidTIMIT (11 synthetic test videos)PSNR: 37.00 -> 38.16Improved
compare running time with Su et al. at the larger resolutionFace video deblurring network · Running time 580x610seconds per frame: 0.77s -> 0.70sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy