AI Paper Atlas

Research map / 3D vision / Face and shape

KMTalk: Speech-Driven 3D Facial Animation with Key Motion Embedding

Zhihao Xu, Shengjie Gong, Jiapeng Tang, Lingyu Liang, Yining Huang, Haojie Li, Shuangping Huang

ECCV 2024 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 8 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
use KMTalk instead of SelfTalkspeech-driven 3D facial animation · VOCA-TestLVE (x10^-5 mm): 3.2238 -> 2.2639Improved
use KMTalk instead of SelfTalkspeech-driven 3D facial animation · BIWI-Test-AFDD (x10^-5 mm): 3.5761 -> 2.5446Improved
use KMTalk instead of SelfTalk on VOCA-Test upper-face dynamicsspeech-driven 3D facial animation · VOCA-TestFDD (x10^-7 mm): 4.0912 -> 4.0594No clear effect
add phoneme-based localization of key motions instead of uniform sampling (ablation)KMTalk · BIWI-Test-ALVE (x10^-4 mm): 4.1648 -> 3.9654Improved
add key motion decoder instead of selecting key frames from an existing method's output (ablation)KMTalk · BIWI-Test-AFDD (x10^-5 mm): 2.9546 -> 2.5446Improved
add audio guidance in cross-modal motion completion (ablation)KMTalk · BIWI-Test-ALVE (x10^-4 mm): 4.8859 -> 3.9654Improved
swap the ASR used for phoneme extraction (Auto-avsr to Whisper) (ablation)KMTalk · BIWI-Test-AFDD (x10^-5 mm): 2.5446 -> 2.8141 (Whisper-large)No clear effect
shift key motion indices by one frame (ablation)KMTalk · BIWI-Test-AFDD (x10^-5 mm): 2.5446 -> 2.6420No clear effect
apply the key-motion progressive learning scheme to existing methodsFaceFormer, CodeTalker, SelfTalk · BIWI-Test-AFDD (x10^-5 mm): SelfTalk 3.5761 -> 2.8668Improved

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