AI Paper Atlas

Research map / Video / Video generation

Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation

Yue Ma, Zexuan Yan, Hongyu Liu, Hongfa Wang, Heng Pan, Yingqing He, Junkun Yuan, Ailing Zeng, Chengfei Cai, Heung‐Yeung Shum, Zhen Li, Wei Liu and 2 more

IJCV 2026 · Video › Video generation · approach: Diffusion-based human image animation · 51 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 expression mask to the facial fine-grained loss (ablation)Follow-Your-Emoji-Faster · EmojiBench++ cross reenactmentlandmark accuracy: 27.52 -> 38.26Improved
add identity (facial) mask to the facial fine-grained loss (ablation)Follow-Your-Emoji-Faster · EmojiBench++ cross reenactmentID similarity: 0.557 -> 0.761Improved
add progressive strategy for long video (ablation)Follow-Your-Emoji-Faster · EmojiBench++ self reenactmentFVD: 135.2 -> 115.4Improved
use expression-aware landmarks instead of standard 2D landmarks (ablation)Follow-Your-Emoji-Faster · EmojiBench++ cross reenactmentlandmark accuracy: 15.92 -> 38.26Improved
exclude facial contour points from landmarks (ablation)Follow-Your-Emoji-Faster · EmojiBench++ cross reenactmentID similarity: 0.634 -> 0.761Improved
add pupil points to landmarks (ablation)Follow-Your-Emoji-Faster · EmojiBench++ self reenactmentFVD: 122.9 -> 115.4Improved
add Taylor interpolation to the cache (ablation)Follow-Your-Emoji-Faster · EmojiBench++ self reenactmentSSIM: 0.782 -> 0.829Improved
add landmark-mask guidance to the cache (ablation)Follow-Your-Emoji-Faster · EmojiBench++ cross reenactmentID similarity: 0.711 -> 0.761Improved
increase cache refresh interval N from 2 to 3 (ablation)TIC · EmojiBench++ accelerationspeedup: 1.71x -> 2.58xMixed
raise Taylor order O from 1 to 3 at N=2 (ablation)TIC · EmojiBench++ cross reenactmentlandmark accuracy: 36.92 -> 37.83Improved
add landmark mask to TIC with N=3 (ablation)TIC · EmojiBench++ self reenactmentFVD: 127.3 -> 115.4Improved
halve the denoising steps to speed up inferenceFollow-Your-Emoji · EmojiBench++ self reenactmentFVD: 118.7 -> 188.6Hurt

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