Saved in:
Bibliographic Details
Main Authors: Xu, Ziyi, Huang, Ziyao, Cao, Juan, Zhang, Yong, Cun, Xiaodong, Shuai, Qing, Wang, Yuchen, Bao, Linchao, Li, Jintao, Tang, Fan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.17383
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915354245070848
author Xu, Ziyi
Huang, Ziyao
Cao, Juan
Zhang, Yong
Cun, Xiaodong
Shuai, Qing
Wang, Yuchen
Bao, Linchao
Li, Jintao
Tang, Fan
author_facet Xu, Ziyi
Huang, Ziyao
Cao, Juan
Zhang, Yong
Cun, Xiaodong
Shuai, Qing
Wang, Yuchen
Bao, Linchao
Li, Jintao
Tang, Fan
contents The generation of anchor-style product promotion videos presents promising opportunities in e-commerce, advertising, and consumer engagement. Despite advancements in pose-guided human video generation, creating product promotion videos remains challenging. In addressing this challenge, we identify the integration of human-object interactions (HOI) into pose-guided human video generation as a core issue. To this end, we introduce AnchorCrafter, a novel diffusion-based system designed to generate 2D videos featuring a target human and a customized object, achieving high visual fidelity and controllable interactions. Specifically, we propose two key innovations: the HOI-appearance perception, which enhances object appearance recognition from arbitrary multi-view perspectives and disentangles object and human appearance, and the HOI-motion injection, which enables complex human-object interactions by overcoming challenges in object trajectory conditioning and inter-occlusion management. Extensive experiments show that our system improves object appearance preservation by 7.5\% and doubles the object localization accuracy compared to existing state-of-the-art approaches. It also outperforms existing approaches in maintaining human motion consistency and high-quality video generation. Project page including data, code, and Huggingface demo: https://github.com/cangcz/AnchorCrafter.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17383
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation
Xu, Ziyi
Huang, Ziyao
Cao, Juan
Zhang, Yong
Cun, Xiaodong
Shuai, Qing
Wang, Yuchen
Bao, Linchao
Li, Jintao
Tang, Fan
Computer Vision and Pattern Recognition
The generation of anchor-style product promotion videos presents promising opportunities in e-commerce, advertising, and consumer engagement. Despite advancements in pose-guided human video generation, creating product promotion videos remains challenging. In addressing this challenge, we identify the integration of human-object interactions (HOI) into pose-guided human video generation as a core issue. To this end, we introduce AnchorCrafter, a novel diffusion-based system designed to generate 2D videos featuring a target human and a customized object, achieving high visual fidelity and controllable interactions. Specifically, we propose two key innovations: the HOI-appearance perception, which enhances object appearance recognition from arbitrary multi-view perspectives and disentangles object and human appearance, and the HOI-motion injection, which enables complex human-object interactions by overcoming challenges in object trajectory conditioning and inter-occlusion management. Extensive experiments show that our system improves object appearance preservation by 7.5\% and doubles the object localization accuracy compared to existing state-of-the-art approaches. It also outperforms existing approaches in maintaining human motion consistency and high-quality video generation. Project page including data, code, and Huggingface demo: https://github.com/cangcz/AnchorCrafter.
title AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.17383