ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
Abstract
ReDirector uses a novel camera-controlled video retake method with Rotary Camera Encoding (RoCE) to improve dynamic object localization and static background preservation in variable-length videos.
We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions of the input video and the target retake. Moreover, we introduce Rotary Camera Encoding (RoCE), a camera-conditioned RoPE phase shift that captures and integrates multi-view relationships within and across the input and target videos. By integrating camera conditions into RoPE, our method generalizes to out-of-distribution camera trajectories and video lengths, yielding improved dynamic object localization and static background preservation. Extensive experiments further demonstrate significant improvements in camera controllability, geometric consistency, and video quality across various trajectories and lengths.
Community
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
- PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention (2025)
- 3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation (2025)
- ShapeGen4D: Towards High Quality 4D Shape Generation from Videos (2025)
- Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures (2025)
- SEE4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting (2025)
- VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos (2025)
- Arbitrary Generative Video Interpolation (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 1
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper