CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Qinghe, Luo, Yawen, Shi, Xiaoyu, Jia, Xu, Lu, Huchuan, Xue, Tianfan, Wang, Xintao, Wan, Pengfei, Zhang, Di, Gai, Kun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913688463605760
author Wang, Qinghe
Luo, Yawen
Shi, Xiaoyu
Jia, Xu
Lu, Huchuan
Xue, Tianfan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
author_facet Wang, Qinghe
Luo, Yawen
Shi, Xiaoyu
Jia, Xu
Lu, Huchuan
Xue, Tianfan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
contents In this work, we present CineMaster, a novel framework for 3D-aware and controllable text-to-video generation. Our goal is to empower users with comparable controllability as professional film directors: precise placement of objects within the scene, flexible manipulation of both objects and camera in 3D space, and intuitive layout control over the rendered frames. To achieve this, CineMaster operates in two stages. In the first stage, we design an interactive workflow that allows users to intuitively construct 3D-aware conditional signals by positioning object bounding boxes and defining camera movements within the 3D space. In the second stage, these control signals--comprising rendered depth maps, camera trajectories and object class labels--serve as the guidance for a text-to-video diffusion model, ensuring to generate the user-intended video content. Furthermore, to overcome the scarcity of in-the-wild datasets with 3D object motion and camera pose annotations, we carefully establish an automated data annotation pipeline that extracts 3D bounding boxes and camera trajectories from large-scale video data. Extensive qualitative and quantitative experiments demonstrate that CineMaster significantly outperforms existing methods and implements prominent 3D-aware text-to-video generation. Project page: https://cinemaster-dev.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08639
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
Wang, Qinghe
Luo, Yawen
Shi, Xiaoyu
Jia, Xu
Lu, Huchuan
Xue, Tianfan
Wang, Xintao
Wan, Pengfei
Zhang, Di
Gai, Kun
Computer Vision and Pattern Recognition
In this work, we present CineMaster, a novel framework for 3D-aware and controllable text-to-video generation. Our goal is to empower users with comparable controllability as professional film directors: precise placement of objects within the scene, flexible manipulation of both objects and camera in 3D space, and intuitive layout control over the rendered frames. To achieve this, CineMaster operates in two stages. In the first stage, we design an interactive workflow that allows users to intuitively construct 3D-aware conditional signals by positioning object bounding boxes and defining camera movements within the 3D space. In the second stage, these control signals--comprising rendered depth maps, camera trajectories and object class labels--serve as the guidance for a text-to-video diffusion model, ensuring to generate the user-intended video content. Furthermore, to overcome the scarcity of in-the-wild datasets with 3D object motion and camera pose annotations, we carefully establish an automated data annotation pipeline that extracts 3D bounding boxes and camera trajectories from large-scale video data. Extensive qualitative and quantitative experiments demonstrate that CineMaster significantly outperforms existing methods and implements prominent 3D-aware text-to-video generation. Project page: https://cinemaster-dev.github.io/.
title CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.08639