AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation
Ziyi Xu, Ziyao Huang, Juan Cao, Yong Zhang, Xiaodong Cun, Qing Shuai, Yuchen Wang, Linchao Bao, Jintao Li, Fan Tang

TL;DR
AnchorCrafter is a diffusion-based system that generates high-quality, controllable human-object interaction videos for product promotion, addressing key challenges in visual fidelity and interaction realism in e-commerce advertising.
Contribution
The paper introduces novel HOI-appearance perception and HOI-motion injection techniques to improve human-object interaction video generation.
Findings
Object appearance preservation improved by 7.5%.
Object localization accuracy doubled.
Outperforms existing methods in motion consistency.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation
