AI Paper Atlas

Research map / Video / Video generation

UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model

Xiangyu Fan, Jiaqi Li, Zhiqian Lin, Weiye Xiao, Lei Yang

ECCV 2024 · Video › Video generation · approach: Talking face generation · 19 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
train one UniTalker on all of A2F-Bench instead of BIWI only (ablation)UniTalker-B · BIWI-Test-ALVE (x10^-4): 4.3681 -> 4.0804Improved
scale training to A2F-Bench for small datasets (ablation)UniTalker-L · BIWI and VocasetLVE: 4.279 -> 3.859 (BIWI)Improved
mix large HDTF with other datasets (ablation)UniTalker-L · D3 (3D-ETF-HDTF)LVE (x10^-6 m^2): 8.445 -> 8.991Hurt
mix Chinese speech with other datasets (ablation)UniTalker-L · D6 (Chinese speech)LVE (x10^-5 m^2): 1.043 -> 1.145Hurt
fine-tune the pre-trained UniTalker on each seen datasetUniTalker-L · A2F-Bench (8 datasets)LVE: average LVE drop 6.3%Improved
initialize from pre-trained UniTalker encoder instead of Wav2vec2-xlsr-53 for unseen annotationBIWI fine-tuning · BIWI (D0) subsetsLVE (x10^-4): 4.249 -> 4.197 with half the dataImproved
multi-head model instead of preprocessing all annotations to FLAME vertices (ablation)UniTalker · VOCA-Test (D1)LVE (x10^-6 m^2): 8.7532 -> 8.3035Improved
add PCA and decoder warm-up to the multi-head model (ablation)UniTalker · multi-dataset training stabilitytraining convergenceImproved
add pivot identity embedding (ablation)UniTalker · cross-ID inferenceface motion qualityImproved
remove autoregression from FaceFormer (ablation)FaceFormer · BIWI-Test-Ainference time (s): 0.705 -> 0.024Improved
use TCN instead of transformer as motion decoder (ablation)UniTalker-L · A2F-Bench D0-D7LVE: 3.971 -> 3.859 (D0)Mixed
place frequency adaptor behind the transformer encoder (ablation)UniTalker-L · A2F-Bench D0-D7LVE: 3.951 -> 3.859 (D0)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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