AI Paper Atlas

Research map / Video / Video generation

DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion

Maksim Siniukov, Di Chang, Minh Tran, Hongkun Gong, Ashutosh Chaubey, Mohammad Soleymani

ICCV 2025 · Video › Video generation · approach: Talking face generation · 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
generate listener video directly in pixel space with video diffusion instead of 3DMM motion codes plus rendererDiTaiListener · ViCo test FIDFID: 49.75 -> 10.14Improved
generate listener video directly in pixel space with video diffusionDiTaiListener · RealTalk test FIDFID: 30.55 -> 7.99Improved
add CTM-Adapter (causal temporal attention) in place of non-causal spatial attention (ablation)DiTaiListener · ViCo test FIDFID: 11.56 -> 10.14Improved
add CTM-Adapter (ablation)DiTaiListener · RealTalk test FD expression (3DMM)FD (expression): 15.10 -> 14.28Improved
add text control (ablation)DiTaiListener · ViCo test FD expression (3DMM)FD (expression): 18.88 -> 17.49Improved
add text control (ablation)DiTaiListener · RealTalk test FD expression (3DMM)FD (expression): 15.62 -> 14.28Improved
add text control (ablation)DiTaiListener · ViCo test FVDFVD: 57.71 -> 53.54Improved
add CTM-Adapter (ablation)DiTaiListener · ViCo test PSNR/LPIPSPSNR: 20.77 vs 20.77No clear effect
add CTM-Adapter (ablation)DiTaiListener · ViCo test SID pose (3DMM)SID (pose): 3.71 -> 3.74Hurt
use DiTaiListener-Edit frame smoothing for long videos instead of prompt travel or teacher forcing (ablation)DiTaiListener long video generation · qualitative long video comparisonsmoothness / transition artifactsImproved
compare against 3DMM-based baselines in user studyDiTaiListener · ViCo user studyoverall preference: 12.83% -> 64.03%Improved

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