AI Paper Atlas

Research map / Video / Video generation

Audio-Driven Co-Speech Gesture Video Generation

Xian Liu, Qianyi Wu, Hang Zhou, Yuanqi Du, Wayne Wu, Dahua Lin, Ziwei Liu

NeurIPS 2022 · Video › Video generation · approach: Video-to-audio synthesis · 14 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
quantize gesture motion into codebooks (vs predicting continuous motion) (ablation)ANGIE · PATSFGD: 5.86 -> 1.35Improved
quantize position-irrelevant relative motion (delta mu, delta L) instead of absolute (ablation)ANGIE · PATSL1 reconstruction: 0.058 -> 0.037Improved
quantize relative delta mu only vs relative delta L only (ablation)ANGIE · PATSL1 reconstruction: 0.052 -> 0.043Improved
add motion refinement residual network (ablation)ANGIE · PATSbeat consistency: 0.58 -> 0.72Improved
add motion refinement residual network (ablation)ANGIE · PATSFGD: 1.39 -> 1.35No clear effect
add motion refinement residual network (ablation)ANGIE · PATSperceptual loss: 48.1 -> 42.9Improved
remove cholesky decomposition constraint (ablation)ANGIE · PATSimage generationHurt
use ANGIE vs SDT baselineSDT · PATS OliverFGD: 1.04 -> 0.88Improved
use unseen audio at test timeANGIE · PATSFGD: 1.35 -> 1.46Hurt
concatenate text features with audio (ablation)ANGIE · PATSFGD: 1.35 -> 1.30Improved

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