cs.CVNov 5, 2026

Compact Motion Embeddings for Feed-forward Unified Human Animation

Authors: Seonwook Park, Hyunsoo Cha, Amrita Mazumdar, Shengze Wang, Tianye Li, Hanbyul Joo, Koki Nagano, Shalini De Mello

Organizations: NVIDIA · Seoul National University

Abstract

Animating a reference image with a driver's motion requires a motion representation that captures face, hand, and body articulation but excludes the driver's appearance. Most body animation methods take motion from external pose estimators and render it with many denoising steps; compact learned motion representations mostly cover the face. We present FUHA, a real-time-capable feed-forward transformer that learns a compact motion embedding of the whole human and uses it for face, upper-body, and full-body animation. A Q-Former compresses the driver's features from a frozen visual encoder into this embedding. To disentangle motion from appearance, a novel contrastive loss pulls it toward the motion embedding of the driver's rendered keypoint image and away from that of the same person in another pose. At inference time, FUHA needs no external pose estimators, keypoints, or parametric body models. As a retrieval key, the motion embedding matches body pose better than the learned global embeddings of ten vision encoders. Its same-person retrieval rate is 0.1%, against 9.5% for its own DINOv3 backbone. On our upper-body benchmark, FUHA outperforms all baselines on every self-reenactment metric and on cross-reenactment identity similarity. It is competitive on face and full-body and runs at up to 38.9 FPS at 512x512 on a single RTX 4090.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy

    Jun 5, 2026Yuan Zeng, Yujia Shi, Yuhao Yang +4Video Diffusion ModelsHuman Motion Generation

  2. FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction

    May 14, 2026Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie +33D Gaussian Splatting3D Reconstruction

  3. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    Jun 29, 2026Jianjiang Yao, Ke Xian, Renxiang Dai +1Feed-Forward 3D Reconstruction4D Reconstruction