ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Object LocalizationSimilar Papers 제목 키워드 기반
RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers
Diffusion Transformers (DiTs) achieve strong video generation quality, but their dense spatiotemporal self-attention scales quadratically with sequence length and quickly becomes the dominant inference bottleneck. Sparse…
Video GenerationDRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling
Accurate and efficient modeling of agent interactions is essential for trajectory generation, the core of autonomous driving systems. Existing methods, scene-centric, agent-centric, and query-centric frameworks, each pre…
Autonomous DrivingPositionDepth Any Video with Scalable Synthetic Data
Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackle…
Depth EstimationLinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
Text-to-video generation enhances content creation but is highly computationally intensive: The computational cost of Diffusion Transformers (DiTs) scales quadratically in the number of pixels. This makes minute-length v…
GPUMambaText-to-Video GenerationVideo GenerationVRoPE: Rotary Position Embedding for Video Large Language Models
Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Exist…
PositionVideo Understanding