AI Paper Atlas

Research map / 3D vision / Depth and stereo

FG-Portrait: 3D Flow Guided Editable Portrait Animation

Yating Xu, Yunqi Miao, Evangelos Ververas, Jiankang Deng, Jifei Song

CVPR 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 1 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
replace driving landmark condition with 3D flow encoding (ablation)FG-Portrait ControlNet · VFHQ self-reenactmentAPD: 4.001 -> 2.682Improved
replace predicted flow map with 3D flow (ablation)FG-Portrait ControlNet · VFHQ cross-reenactmentAPD: 12.430 -> 7.764Improved
add depth-guided sampling (ablation)3D flow encoding · VFHQ self-reenactmentAPD: 9.659 -> 2.682Improved
add depth-guided sampling (ablation)3D flow encoding · VFHQ self-reenactmentLPIPS: 0.213 -> 0.158Improved
add depth-guided sampling (ablation)3D flow encoding · VFHQ self-reenactmentCSIM: 0.770 -> 0.807Improved
use 3D flow motion condition instead of other diffusion conditionsFG-Portrait · VFHQ self-reenactmentAPD: 3.440 -> 2.682 (vs HunyuanPortrait)Improved
use FG-Portrait instead of baselines on identity preservationFG-Portrait · VFHQ cross-reenactmentCSIM: 0.484 -> 0.462 (vs Follow-Your-Emoji)Hurt
use FG-Portrait instead of baselinesFG-Portrait · FFHQ cross-reenactmentFID: 113.7 -> 99.4 (vs HunyuanPortrait)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