LIA-X: Interpretable Latent Portrait Animator

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yaohui, Yang, Di, Chen, Xinyuan, Bremond, Francois, Qiao, Yu, Dantcheva, Antitza
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912536272568320
author Wang, Yaohui
Yang, Di
Chen, Xinyuan
Bremond, Francois
Qiao, Yu
Dantcheva, Antitza
author_facet Wang, Yaohui
Yang, Di
Chen, Xinyuan
Bremond, Francois
Qiao, Yu
Dantcheva, Antitza
contents We introduce LIA-X, a novel interpretable portrait animator designed to transfer facial dynamics from a driving video to a source portrait with fine-grained control. LIA-X is an autoencoder that models motion transfer as a linear navigation of motion codes in latent space. Crucially, it incorporates a novel Sparse Motion Dictionary that enables the model to disentangle facial dynamics into interpretable factors. Deviating from previous 'warp-render' approaches, the interpretability of the Sparse Motion Dictionary allows LIA-X to support a highly controllable 'edit-warp-render' strategy, enabling precise manipulation of fine-grained facial semantics in the source portrait. This helps to narrow initial differences with the driving video in terms of pose and expression. Moreover, we demonstrate the scalability of LIA-X by successfully training a large-scale model with approximately 1 billion parameters on extensive datasets. Experimental results show that our proposed method outperforms previous approaches in both self-reenactment and cross-reenactment tasks across several benchmarks. Additionally, the interpretable and controllable nature of LIA-X supports practical applications such as fine-grained, user-guided image and video editing, as well as 3D-aware portrait video manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_09959
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LIA-X: Interpretable Latent Portrait Animator
Wang, Yaohui
Yang, Di
Chen, Xinyuan
Bremond, Francois
Qiao, Yu
Dantcheva, Antitza
Computer Vision and Pattern Recognition
We introduce LIA-X, a novel interpretable portrait animator designed to transfer facial dynamics from a driving video to a source portrait with fine-grained control. LIA-X is an autoencoder that models motion transfer as a linear navigation of motion codes in latent space. Crucially, it incorporates a novel Sparse Motion Dictionary that enables the model to disentangle facial dynamics into interpretable factors. Deviating from previous 'warp-render' approaches, the interpretability of the Sparse Motion Dictionary allows LIA-X to support a highly controllable 'edit-warp-render' strategy, enabling precise manipulation of fine-grained facial semantics in the source portrait. This helps to narrow initial differences with the driving video in terms of pose and expression. Moreover, we demonstrate the scalability of LIA-X by successfully training a large-scale model with approximately 1 billion parameters on extensive datasets. Experimental results show that our proposed method outperforms previous approaches in both self-reenactment and cross-reenactment tasks across several benchmarks. Additionally, the interpretable and controllable nature of LIA-X supports practical applications such as fine-grained, user-guided image and video editing, as well as 3D-aware portrait video manipulation.
title LIA-X: Interpretable Latent Portrait Animator
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.09959