Saved in:
Bibliographic Details
Main Authors: Wang, Lizhen, Xia, Zhurong, Hu, Tianshu, Wang, Pengrui, Wei, Pengfei, Zheng, Zerong, Zhou, Ming, Zhang, Yuan, Gao, Mingyuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.10568
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914007960518656
author Wang, Lizhen
Xia, Zhurong
Hu, Tianshu
Wang, Pengrui
Wei, Pengfei
Zheng, Zerong
Zhou, Ming
Zhang, Yuan
Gao, Mingyuan
author_facet Wang, Lizhen
Xia, Zhurong
Hu, Tianshu
Wang, Pengrui
Wei, Pengfei
Zheng, Zerong
Zhou, Ming
Zhang, Yuan
Gao, Mingyuan
contents In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks either fail to preserve the identities of both humans and products or lack an understanding of human-product spatial relationships, leading to unrealistic representations and unnatural interactions. To address these challenges, we propose a Diffusion Transformer (DiT)-based framework. Our method simultaneously preserves human identities and product-specific details, such as logos and textures, by injecting paired human-product reference information and utilizing an additional masked cross-attention mechanism. We employ a 3D body mesh template and product bounding boxes to provide precise motion guidance, enabling intuitive alignment of hand gestures with product placements. Additionally, structured text encoding is used to incorporate category-level semantics, enhancing 3D consistency during small rotational changes across frames. Trained on a hybrid dataset with extensive data augmentation strategies, our approach outperforms state-of-the-art techniques in maintaining the identity integrity of both humans and products and generating realistic demonstration motions. Project page: https://lizhenwangt.github.io/DreamActor-H1/.
format Preprint
id arxiv_https___arxiv_org_abs_2506_10568
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers
Wang, Lizhen
Xia, Zhurong
Hu, Tianshu
Wang, Pengrui
Wei, Pengfei
Zheng, Zerong
Zhou, Ming
Zhang, Yuan
Gao, Mingyuan
Computer Vision and Pattern Recognition
Artificial Intelligence
In e-commerce and digital marketing, generating high-fidelity human-product demonstration videos is important for effective product presentation. However, most existing frameworks either fail to preserve the identities of both humans and products or lack an understanding of human-product spatial relationships, leading to unrealistic representations and unnatural interactions. To address these challenges, we propose a Diffusion Transformer (DiT)-based framework. Our method simultaneously preserves human identities and product-specific details, such as logos and textures, by injecting paired human-product reference information and utilizing an additional masked cross-attention mechanism. We employ a 3D body mesh template and product bounding boxes to provide precise motion guidance, enabling intuitive alignment of hand gestures with product placements. Additionally, structured text encoding is used to incorporate category-level semantics, enhancing 3D consistency during small rotational changes across frames. Trained on a hybrid dataset with extensive data augmentation strategies, our approach outperforms state-of-the-art techniques in maintaining the identity integrity of both humans and products and generating realistic demonstration motions. Project page: https://lizhenwangt.github.io/DreamActor-H1/.
title DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.10568