AI Paper Atlas

Research map / Video / Video generation

Identity-Preserving Video Dubbing Using Motion Warping

Ruzhang Liu, Qinjie Lin, Yunfei Liu, Lijian Lin, Ye Zhu, Yu Li, Chuhua Xian, Fa-Ting Hong

IJCV 2026 · Video › Video generation · approach: Talking face generation · 2 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 the alignment module (AVAU) instead of a conv audio encoder (ablation)IPTalker · HDTFPSNR: 29.6988 -> 30.8796Improved
add the alignment module (AVAU) instead of a conv audio encoder (ablation)IPTalker · HDTFLSE-C: 7.9878 -> 8.2741Improved
add the SPADE decoder instead of a conv decoder (ablation)IPTalker · HDTFPSNR: 29.8337 -> 30.8796Improved
add the SPADE decoder instead of a conv decoder (ablation)IPTalker · HDTFLPIPS: 0.0626 -> 0.0582Improved
add the cross-modalities encoder E_cm (ablation)IPTalker · HDTFLSE-D: 7.2375 -> 7.0218Improved
add the cross-modalities encoder E_cm (ablation)IPTalker · HDTFLSE-C: 8.0697 -> 8.2741Improved
add the cross-modalities encoder E_cm (ablation)IPTalker · HDTFSSIM: 0.6265 -> 0.6365Improved
identity fine-tuning for 300 stepsIPTalker (identity fine-tuning) · HDTFPSNR: 30.8919 -> 34.2662Improved
identity fine-tuning for 100 stepsIPTalker (identity fine-tuning) · HDTFLPIPS: 0.0584 -> 0.0388Improved
increase fine-tuning from 200 to 300 stepsIPTalker (identity fine-tuning) · HDTFLSE-D: 6.9742 -> 6.9888No clear effect
compare IPTalker with DINet (training on HDTF only)IPTalker vs DINet · HDTFPSNR: 27.7341 -> 30.8796Improved
compare IPTalker with Hallo on profile-heavy dataIPTalker vs Hallo · VFHQLSE-C: 6.5482 -> 6.0691Hurt

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