Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Shuai, Gong, Biao, Wang, Xiang, Zhang, Shiwei, Zheng, Dandan, Zheng, Ruobing, Zheng, Kecheng, Chen, Jingdong, Yang, Ming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915057893376000
author Tan, Shuai
Gong, Biao
Wang, Xiang
Zhang, Shiwei
Zheng, Dandan
Zheng, Ruobing
Zheng, Kecheng
Chen, Jingdong
Yang, Ming
author_facet Tan, Shuai
Gong, Biao
Wang, Xiang
Zhang, Shiwei
Zheng, Dandan
Zheng, Ruobing
Zheng, Kecheng
Chen, Jingdong
Yang, Ming
contents Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X, a universal animation framework based on LDM for various character types (collectively named X), including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of LDM by simulating possible inputs in advance that may arise during inference. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A^2Bench) to evaluate the performance of Animate-X on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2410_10306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Animate-X: Universal Character Image Animation with Enhanced Motion Representation
Tan, Shuai
Gong, Biao
Wang, Xiang
Zhang, Shiwei
Zheng, Dandan
Zheng, Ruobing
Zheng, Kecheng
Chen, Jingdong
Yang, Ming
Computer Vision and Pattern Recognition
Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X, a universal animation framework based on LDM for various character types (collectively named X), including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of LDM by simulating possible inputs in advance that may arise during inference. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A^2Bench) to evaluate the performance of Animate-X on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X compared to state-of-the-art methods.
title Animate-X: Universal Character Image Animation with Enhanced Motion Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.10306