Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Bohan, Yang, Ling, Li, Siyu, Liu, Jiaming, Zhang, Zixiang, Tian, Juanxi, Zhu, Kaixin, Guo, Yongzhen, Wang, Fu-Yun, Xu, Minkai, Ermon, Stefano, Zhang, Wentao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916429635256320
author Zeng, Bohan
Yang, Ling
Li, Siyu
Liu, Jiaming
Zhang, Zixiang
Tian, Juanxi
Zhu, Kaixin
Guo, Yongzhen
Wang, Fu-Yun
Xu, Minkai
Ermon, Stefano
Zhang, Wentao
author_facet Zeng, Bohan
Yang, Ling
Li, Siyu
Liu, Jiaming
Zhang, Zixiang
Tian, Juanxi
Zhu, Kaixin
Guo, Yongzhen
Wang, Fu-Yun
Xu, Minkai
Ermon, Stefano
Zhang, Wentao
contents Recent advances in diffusion models have demonstrated exceptional capabilities in image and video generation, further improving the effectiveness of 4D synthesis. Existing 4D generation methods can generate high-quality 4D objects or scenes based on user-friendly conditions, benefiting the gaming and video industries. However, these methods struggle to synthesize significant object deformation of complex 4D transitions and interactions within scenes. To address this challenge, we propose Trans4D, a novel text-to-4D synthesis framework that enables realistic complex scene transitions. Specifically, we first use multi-modal large language models (MLLMs) to produce a physic-aware scene description for 4D scene initialization and effective transition timing planning. Then we propose a geometry-aware 4D transition network to realize a complex scene-level 4D transition based on the plan, which involves expressive geometrical object deformation. Extensive experiments demonstrate that Trans4D consistently outperforms existing state-of-the-art methods in generating 4D scenes with accurate and high-quality transitions, validating its effectiveness. Code: https://github.com/YangLing0818/Trans4D
format Preprint
id arxiv_https___arxiv_org_abs_2410_07155
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis
Zeng, Bohan
Yang, Ling
Li, Siyu
Liu, Jiaming
Zhang, Zixiang
Tian, Juanxi
Zhu, Kaixin
Guo, Yongzhen
Wang, Fu-Yun
Xu, Minkai
Ermon, Stefano
Zhang, Wentao
Computer Vision and Pattern Recognition
Recent advances in diffusion models have demonstrated exceptional capabilities in image and video generation, further improving the effectiveness of 4D synthesis. Existing 4D generation methods can generate high-quality 4D objects or scenes based on user-friendly conditions, benefiting the gaming and video industries. However, these methods struggle to synthesize significant object deformation of complex 4D transitions and interactions within scenes. To address this challenge, we propose Trans4D, a novel text-to-4D synthesis framework that enables realistic complex scene transitions. Specifically, we first use multi-modal large language models (MLLMs) to produce a physic-aware scene description for 4D scene initialization and effective transition timing planning. Then we propose a geometry-aware 4D transition network to realize a complex scene-level 4D transition based on the plan, which involves expressive geometrical object deformation. Extensive experiments demonstrate that Trans4D consistently outperforms existing state-of-the-art methods in generating 4D scenes with accurate and high-quality transitions, validating its effectiveness. Code: https://github.com/YangLing0818/Trans4D
title Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.07155