Saved in:
Bibliographic Details
Main Authors: Wang, Zhenzhi, Li, Yixuan, Zeng, Yanhong, Fang, Youqing, Guo, Yuwei, Liu, Wenran, Tan, Jing, Chen, Kai, Xue, Tianfan, Dai, Bo, Lin, Dahua
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.17438
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915028456701952
author Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Fang, Youqing
Guo, Yuwei
Liu, Wenran
Tan, Jing
Chen, Kai
Xue, Tianfan
Dai, Bo
Lin, Dahua
author_facet Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Fang, Youqing
Guo, Yuwei
Liu, Wenran
Tan, Jing
Chen, Kai
Xue, Tianfan
Dai, Bo
Lin, Dahua
contents Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches yield impressive results using high-quality training data, the inaccessibility of these datasets hampers fair and transparent benchmarking. Moreover, these approaches prioritize 2D human motion and overlook the significance of camera motions in videos, leading to limited control and unstable video generation. To demystify the training data, we present HumanVid, the first large-scale high-quality dataset tailored for human image animation, which combines crafted real-world and synthetic data. For the real-world data, we compile a vast collection of real-world videos from the internet. We developed and applied careful filtering rules to ensure video quality, resulting in a curated collection of 20K high-resolution (1080P) human-centric videos. Human and camera motion annotation is accomplished using a 2D pose estimator and a SLAM-based method. To expand our synthetic dataset, we collected 10K 3D avatar assets and leveraged existing assets of body shapes, skin textures and clothings. Notably, we introduce a rule-based camera trajectory generation method, enabling the synthetic pipeline to incorporate diverse and precise camera motion annotation, which can rarely be found in real-world data. To verify the effectiveness of HumanVid, we establish a baseline model named CamAnimate, short for Camera-controllable Human Animation, that considers both human and camera motions as conditions. Through extensive experimentation, we demonstrate that such simple baseline training on our HumanVid achieves state-of-the-art performance in controlling both human pose and camera motions, setting a new benchmark. Demo, data and code could be found in the project website: https://humanvid.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17438
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Wang, Zhenzhi
Li, Yixuan
Zeng, Yanhong
Fang, Youqing
Guo, Yuwei
Liu, Wenran
Tan, Jing
Chen, Kai
Xue, Tianfan
Dai, Bo
Lin, Dahua
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Human image animation involves generating videos from a character photo, allowing user control and unlocking the potential for video and movie production. While recent approaches yield impressive results using high-quality training data, the inaccessibility of these datasets hampers fair and transparent benchmarking. Moreover, these approaches prioritize 2D human motion and overlook the significance of camera motions in videos, leading to limited control and unstable video generation. To demystify the training data, we present HumanVid, the first large-scale high-quality dataset tailored for human image animation, which combines crafted real-world and synthetic data. For the real-world data, we compile a vast collection of real-world videos from the internet. We developed and applied careful filtering rules to ensure video quality, resulting in a curated collection of 20K high-resolution (1080P) human-centric videos. Human and camera motion annotation is accomplished using a 2D pose estimator and a SLAM-based method. To expand our synthetic dataset, we collected 10K 3D avatar assets and leveraged existing assets of body shapes, skin textures and clothings. Notably, we introduce a rule-based camera trajectory generation method, enabling the synthetic pipeline to incorporate diverse and precise camera motion annotation, which can rarely be found in real-world data. To verify the effectiveness of HumanVid, we establish a baseline model named CamAnimate, short for Camera-controllable Human Animation, that considers both human and camera motions as conditions. Through extensive experimentation, we demonstrate that such simple baseline training on our HumanVid achieves state-of-the-art performance in controlling both human pose and camera motions, setting a new benchmark. Demo, data and code could be found in the project website: https://humanvid.github.io/.
title HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2407.17438