AI Paper Atlas

Research map / Video / Video generation

OmniFace: Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

Xu Guo, Fulong Ye, Xinghui Li, Pengqi Tu, Pengze Zhang, Qichao Sun, Songtao Zhao, Xiangwang Hou, Qian HE

ECCV 2026 · Video › Video generation · approach: Diffusion-based human image animation · 11 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 SyncID-Pipe ID quadruplet supervision instead of self-reconstruction inpainting (ablation)OmniFace · IDBench-VID-Arc: 0.510 -> 0.659Improved
add SyncID-Pipe ID quadruplet supervision instead of self-reconstruction inpainting (ablation)OmniFace · IDBench-VVariance: 0.0036 -> 0.0029Hurt
add synthetic GT data with real GT data (Synthetic-to-Real Training) (ablation)OmniFace · IDBench-VID-Arc: 0.604 -> 0.659Improved
add synthetic GT data with real GT data (Synthetic-to-Real Training) (ablation)OmniFace · IDBench-VVFID: 2.145 -> 2.243Mixed
add real paired data to forward-generated paired data (ablation)OmniFace · IDBench-VVFID: 3.845 -> 2.243Improved
add real paired data to forward-generated paired data (ablation)OmniFace · IDBench-VID-Arc: 0.657 -> 0.659No clear effect
add Identity-Coherence Reward Weighting (IDRW) (ablation)OmniFace · IDBench-VID-Arc: 0.631 -> 0.659Improved
add Identity-Coherence Reward Weighting (IDRW) (ablation)OmniFace · IDBench-VVariance: 0.0041 -> 0.0029Improved
add Identity-Coherence Reward Weighting (IDRW) (ablation)OmniFace · IDBench-VPose error: 2.687 -> 2.446Improved
OmniFace vs DreamID image swapping applied per frameOmniFace · IDBench-VID-Arc: 0.616 -> 0.659Improved
OmniFace vs CanonSwap on pose errorOmniFace · IDBench-VPose error: 2.430 -> 2.446Hurt
OmniFace vs DreamID in user studyOmniFace · User study (19 volunteers)Quality (1-5): 3.06 -> 4.15Improved

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