AI Paper Atlas

Research map / Video / Video generation

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Fa-Ting Hong, Zunnan Xu, Zixiang Zhou, Jun Zhou, Xiu Li, Qin Lin, Qinglin Lu, Dan Xu

ICCV 2025 · Video › Video generation · approach: Talking face generation · 16 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 mask-drop strategy (ablation)ACTalker (audio only) · CelebV-HQSync-C: 4.953 -> 5.317Improved
add mask-drop strategy (ablation)ACTalker (audio only) · CelebV-HQFVD-Inc: 240.651 -> 232.374Improved
add mask-drop strategy (ablation)ACTalker multi-signal · Multi-signal controlcontrol conflictImproved
replace spatial cross-attention with parallel-control mamba layer (ablation)ACTalker (audio only) · CelebV-HQSync-C: 4.592 -> 5.317Improved
replace spatial cross-attention with parallel-control mamba layer (ablation)ACTalker (audio only) · CelebV-HQFVD-Inc: 268.512 -> 232.374Improved
add identity embedding in PCM (ablation)ACTalker (audio only) · CelebV-HQSync-C: 5.241 -> 5.317Improved
add identity embedding in PCM (ablation)ACTalker (audio only) · CelebV-HQFVD-Inc: 247.933 -> 232.374Improved
add facial motion signal to audio control (ablation)ACTalker · CelebV-HQSync-C: 5.317 -> 5.737Improved
add facial motion signal to audio control (ablation)ACTalker · RAVDESSSync-C: 5.334 -> 5.511Improved
ACTalker versus MemoACTalker (audio only) · CelebV-HQFVD-Inc: 264.596 -> 232.374Improved
ACTalker versus X-PortraitACTalker · VFHQ cross reenactmentExpression Similarity: 0.48 -> 0.57Improved

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