发表机构
The Chinese University of Hong Kong; Ant Group; Tsinghua University; Zhejiang University; The Hong Kong University of Science and Technology（香港中文大学; 蚂蚁集团; 清华大学; 浙江大学; 香港科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CameraAnything是用于相机控制视频编辑的统一框架，采用逐像素普吕克光线注入等方法联合控制相机参数，开发合成管道克服数据稀缺，能在单过程中实现多种视频编辑操作，为视频制作提供实用价值。
AI 中文摘要
我们介绍了CameraAnything，这是首个用于相机控制视频编辑的统一框架，可对相机的内参和外参进行联合控制。现有方法要么依赖昂贵的3D重建来实现完整相机功能，要么将编辑限制在外参操作上。此外，内参和外参对视频外观的耦合影响使得解缠建模颇具挑战。为此，我们采用逐像素普吕克光线注入以及自注意力中分辨率感知的3D RoPE，在目标潜空间上构建相机条件和空间位置编码，以联合控制相机位置、焦距和原生分辨率编辑，无需裁剪或补绘。为克服配对训练数据的稀缺性，我们进一步开发了一个可扩展的合成管道，通过结构化多相机记录构建多样动态场景，并生成具有不同相机配置的同步视频。通过定制的正交训练策略，CameraAnything能够在单个生成过程中进行具有任意视点控制、焦距调整、分辨率适配和多镜头过渡的富有表现力的视频重新拍摄，为电影视频编辑和视频制作中的跨平台内容适配提供了强大的实用价值。
英文摘要
We introduce CameraAnything, the first unified framework for camera controlled video editing that enables joint control of both intrinsic and extrinsic camera parameters. Existing approaches either rely on expensive 3D reconstruction to achieve full camera functionality or restrict editing to extrinsic parameter manipulation. Moreover, the coupled influence of intrinsic and extrinsic parameters on video appearance makes disentangled modeling particularly challenging. To address this, we adopt per-pixel Plücker ray injection alongside resolution-aware 3D RoPE in self-attention, building both camera conditioning and spatial positional encoding on the target latent to jointly control camera position, focal length, and native resolution editing without cropping or outpainting. To overcome the scarcity of paired training data, we further develop a scalable synthetic pipeline that constructs diverse dynamic scenes through structured multi-camera recording and generates synchronized videos with varied camera configurations. With a tailored orthogonal training strategy, CameraAnything enables expressive video reshooting with arbitrary viewpoint control, focal length adjustment, resolution adaptation, and multi-shot transitions within a single generation process, offering strong practical value for cinematic video editing and cross-platform content adaptation in video production.
CommentsProject page: https://yixuanli98.github.io/cameraanything/
