AI Paper Atlas

Research map / Video / Video generation

Talking-head Generation with Rhythmic Head Motion

Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu

ECCV 2020 · Video › Video generation · approach: Talking face generation · 192 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 3D-Aware module (ablation)Full model · VoxCeleb2 (ablation, from scratch)FID: 109 -> 40.8Improved
add 3D-Aware module (ablation)Full model · VoxCeleb2 (ablation, from scratch)CSIM: 0.21 -> 0.44Improved
add 3D-Aware module (ablation)Full model · VoxCeleb2 (ablation, from scratch)SSIM: 0.61 -> 0.71Improved
add hybrid attention embedding (ablation)Full model · VoxCeleb2 (ablation, from scratch)FID: 57.8 -> 40.8Improved
add hybrid attention embedding (ablation)Full model · VoxCeleb2 (ablation, from scratch)SSIM: 0.73 -> 0.71Hurt
add hybrid attention embedding (ablation)Full model · VoxCeleb2 (ablation, from scratch)CSIM: 0.37 -> 0.44Improved
add non-linear composition module (ablation)Full model · VoxCeleb2 (ablation, from scratch)FID: 64.5 -> 40.8Improved
add non-linear composition module (ablation)Full model · VoxCeleb2 (ablation, from scratch)CSIM: 0.40 -> 0.44Improved
add warping operation (ablation)Full model · VoxCeleb2 (ablation, from scratch)FID: 78.2 -> 40.8Improved
add warping operation (ablation)Full model · VoxCeleb2 (ablation, from scratch)CSIM: 0.34 -> 0.44Improved
increase number of reference frames K from 1 to 32Ours · VoxCeleb2 (landmark-driven)FID: 40.8 -> 37.1 -> 35.7Improved
increase number of reference frames K from 1 to 32Ours · LRS3-TED (landmark-driven)SSIM: 0.71 -> 0.76 -> 0.79Improved

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