AI Paper Atlas

Research map / Video / Video generation

Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers

Yasheng Sun, Zhiliang Xu, Hang Zhou, Jiazhi Guan, Quanwei Yang, Kaisiyuan Wang, Borong Liang, Yingying Li, Haocheng Feng, Jingdong Wang, Ziwei Liu, Koike Hideki

IJCV 2026 · Video › Video generation · approach: Talking face generation · 4 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 AM-DiT iterative blocks (ablation)Cosh-DiT · Co-speech gesture video (ablation)FID: FID 84.22 -> 77.51Improved
add AM-DiT iterative blocks (ablation)Cosh-DiT · Co-speech gesture video (ablation)IDSim: IDSim 0.5742 -> 0.5918Improved
add spatial alignment of 2D skeleton and 3D hand mesh (ablation)Cosh-DiT · Co-speech gesture video (ablation)FID: FID 89.24 -> 77.51Improved
add spatial alignment of 2D skeleton and 3D hand mesh (ablation)Cosh-DiT · Co-speech gesture video (ablation)Conf-body: Conf-body 0.8723 -> 0.9343Improved
add spatial alignment of 2D skeleton and 3D hand mesh (ablation)Cosh-DiT · Co-speech gesture video (ablation)IDSim: IDSim 0.5423 -> 0.5918Improved
add hybrid motion with 3D hand guidance (ablation)Cosh-DiT · Co-speech gesture video (ablation)Conf-hand: Conf-hand 0.8623 -> 0.8937Improved
add hybrid motion with 3D hand guidance (ablation)Cosh-DiT · Co-speech gesture video (ablation)SSIM: SSIM 0.6584 -> 0.6729Improved
add AM-DiT iterative blocks (ablation)Cosh-DiT · Co-speech gesture video (ablation)SSIM: SSIM 0.6323 -> 0.6729Improved
use Cosh-DiT-V instead of ControlNeXt for pose-driven animationCosh-DiT-V · Motion animation with pose inputFID: FID 55.64 -> 24.62Improved
compare against S2G-MDD GAN-based renderingCosh-DiT · Co-speech gesture video (S2G-MDD evaluation data)FVD: FVD 1201.72 -> 881.83Improved

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