PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention
By: Yipeng Chen , Zhichao Ye , Zhenzhou Fang and more
Potential Business Impact:
Changes camera views in videos after they are filmed.
We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection strategies; such suboptimal designs not only limit camera control precision but also result in generated videos that fail to preserve fine visual details from the source video. To achieve more accurate and flexible motion manipulation, PostCam introduces a query-shared cross-attention module. It integrates two distinct forms of control signals: the 6-DoF camera poses and the 2D rendered video frames. By fusing them into a unified representation within a shared feature space, our model can extract underlying motion cues, which enhances both control precision and generation quality. Furthermore, we adopt a two-stage training strategy: the model first learns coarse camera control from pose inputs, and then incorporates visual information to refine motion accuracy and enhance visual fidelity. Experiments on both real-world and synthetic datasets demonstrate that PostCam outperforms state-of-the-art methods by over 20% in camera control precision and view consistency, while achieving the highest video generation quality. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/
Similar Papers
Track and Caption Any Motion: Query-Free Motion Discovery and Description in Videos
CV and Pattern Recognition
Lets computers describe what's happening in videos.
Generative Photographic Control for Scene-Consistent Video Cinematic Editing
CV and Pattern Recognition
Lets you change movie look like a pro.
VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos
CV and Pattern Recognition
Makes videos with amazing camera moves.