让视频视角控制更准，细节更清晰。
PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention
- 用共享查询的跨注意力机制对齐姿态与图像特征
- 轨迹精度比现有方法高20%，动态场景更稳定
- 适合需要精准视角编辑的视频生成任务
我们提出 PostCam，一种简洁高效的新型视角视频生成框架，可在动态场景中同时实现优异的细节保留和精确的相机轨迹编辑。现有方法常在基于姿态的控制（缺乏视觉细节）与基于渲染的引导（依赖几何精度）之间权衡。尽管近期有混合尝试，但精确运动与视觉一致性仍难兼顾，主要因跨模态对齐不足。我们认为，鲁棒控制源于多模态信号的深层对齐，而非输入复杂度提升。核心贡献是查询共享的跨注意力机制，将6-DoF姿态与渲染特征投影至统一潜在空间，使模型在去噪过程中自发实现运动线索与像素级引导的内在一致。实验表明，PostCam 在保持高保真视觉细节的同时，轨迹精度较最先进方法提升20%，在复杂动态场景中表现更优。项目主页已公开：https://cccqaq.github.io/PostCam.github.io/
原文摘要 · Abstract (English)
We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory editing in dynamic scenes. Current methods often struggle with a trade-off between pose-based control, which lacks visual detail, and rendering-based guidance, which is overly sensitive to geometric accuracy. Despite recent hybrid attempts, achieving precise motion and visual consistency remains challenging due to the lack of effective cross-modal alignment. We argue that robust control stems from the deep alignment of multimodal signals rather than increased input complexity. Our core contribution is the Query-Shared Cross-Attention mechanism, which projects 6-DoF poses and rendered features into a unified latent space. This allows the model to spontaneously achieve intrinsic consistency between motion cues and pixel-level guidance during denoising. Experiments demonstrate that PostCam maintains high-fidelity visual details while outperforming state-of-the-art methods by 20% in trajectory precision, exhibiting superior robustness in complex dynamic scenes. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。