Lune

CVPR2025顶会

Exploring Timeline Control for Facial Motion Generation

Yifeng Ma, Jinwei Qi, Chaonan Ji, Peng Zhang, Bang Zhang, Zhidong Deng, Liefeng Bo

2025年份
1顶会引用

摘要

Brow Brow Up Eye Close Widen Squint Mouth Smile Gaze Gaze right Pose Head Left&Down Head Right Head Left (Rendered) Facial motions aligned with timelines User-specified facial motion timelines Time … Brow Brow Down Brow Up Eye Squint Widen Mouth Smile Gaze Gaze right Pose Head Right Natural facial motion sequences Facial motion timelines from annotation Time … Annotate 2 4 (sec) 0 2 4 (sec) 0 Figure 1. We introduce a new control signal for facial motion generation: timeline control. We first utilize a labor-efficient approach to annotate the time intervals of facial motion at a frame-level granularity. Using the annotations, we propose a model that can generate natural facial motions aligned with an input timeline. Compared to previous controls like audio and text, timeline control enables precise temporal control of facial motions. In this paper, facial motions are rendered into photorealistic videos for better visualization.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper1

问问它们各自怎么用它

它引用的顶会 Paper22

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖