ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Abstract
Camera control has been actively studied in text or image conditioned video generation tasks. However, altering camera trajectories of a given video remains under-explored, despite its importance in the field of video creation. It is non-trivial due to the extra constraints of maintaining multiple-frame appearance and dynamic synchronization. To address this, we present ReCamMaster, a camera-controlled generative video re-rendering framework that reproduces the dynamic scene of an input video at novel camera trajectories. The core innovation lies in harnessing the generative capabilities of pre-trained text-to-video models through a simple yet powerful video conditioning mechanism -- its capability often overlooked in current research. To overcome the scarcity of qualified training data, we construct a comprehensive multi-camera synchronized video dataset using Unreal Engine 5, which is carefully curated to follow real-world filming characteristics, covering diverse scenes and camera movements. It helps the model generalize to in-the-wild videos. Lastly, we further improve the robustness to diverse inputs through a meticulously designed training strategy. Extensive experiments tell that our method substantially outperforms existing state-of-the-art approaches and strong baselines. Our method also finds promising applications in video stabilization, super-resolution, and outpainting. Project page: https://jianhongbai.github.io/ReCamMaster/
Community
Project Page: https://jianhongbai.github.io/ReCamMaster
Try ReCamMaster with Your Own Videos: https://github.com/KwaiVGI/ReCamMaster
Hey I was trying to look for any open source code to deploy recammaster but the github repo link only has 3 txt files, one of which was a link to a google doc file. Other than some demos, there’s no code?
Thank you for your interest in our work! Currently, ReCamMaster is an internal model, and due to company policies, we are unable to open-source the code. However, you can try out our model by uploading your own video to this link, and we will send the inference results to your email.
If you would like to use ReCamMaster as a baseline and need qualitative or quantitative comparisons, please feel free to drop an email to [email protected]. We can assist you with batch inference of our model.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Reangle-A-Video: 4D Video Generation as Video-to-Video Translation (2025)
- TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models (2025)
- CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models (2025)
- GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control (2025)
- MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation (2025)
- I2V3D: Controllable image-to-video generation with 3D guidance (2025)
- Get In Video: Add Anything You Want to the Video (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper