AI Paper Atlas

Research map / 3D vision / Face and shape

RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with Neural Appearance Priors

Lei Zhu, Lijian Lin, Ye Zhu, Xuehan Hou, Jiahao Wu, Yu Li, Yunfei Liu, Jie Chen

ECCV 2026 · 3D vision › Face and shape · approach: Speech-driven 3D facial animation · 0 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 dual-audio fusion module (ablation)DiffPoseTalk baseline · Real-Dialog testLVE: 0.269 -> 0.193Improved
add dual-audio fusion module (ablation)DiffPoseTalk baseline · Real-Dialog testPSNR: 18.97 -> 20.17Improved
add dual-audio fusion module (ablation)DiffPoseTalk baseline · Real-Dialog testFDD: 1.607 -> 1.603No clear effect
add residual audio connection (ablation)audio fusion · Real-Dialog testLVE: 0.193 -> 0.233Hurt
add residual audio connection (ablation)audio fusion · Real-Dialog testMOD: 1.281 -> 1.230Improved
add speaking indicator (ablation)audio fusion + residual · Real-Dialog testSLCC: 0.683 -> 0.698Improved
add speaking indicator (ablation)audio fusion + residual · Real-Dialog testMTM: 4.371 -> 4.526Hurt
add jaw pose loss (ablation)previous variant · Real-Dialog testSLCC: 0.698 -> 0.802Improved
add second-stage 2D photometric supervision with alternating training (ablation)stage-1 model · Real-Dialog testLVE: 0.235 -> 0.174Improved
add second-stage 2D photometric supervision with alternating training (ablation)stage-1 model · Real-Dialog testPSNR: 21.20 -> 23.25Improved
add second-stage 2D photometric supervision with alternating training (ablation)stage-1 model · Real-Dialog testSLCC: 0.802 -> 0.791Hurt
use RealDyadic instead of Spectre tracking as mesh sourcelip keypoint accuracy · manually annotated keypointsMAELip: 9.68 -> 6.23Improved

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