arXiv cs.AI· Shuai Li, Jinxu Xiang, Xinyuan Li, Hanlei Guo, Xiyang Tan, Alan Zhao, Xiaotong Zhao, Ran Zhang·· 3 天前AI 评分31
Gen Through the Lens：跨坐标系条件融合的相机可控视频生成
Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion
AI 导读
Gen Through the Lens 是一个相机可控的图像到视频生成框架，通过跨坐标系条件融合，将相机坐标（内参）、世界坐标（空间几何提示）和物体坐标（目标主体的 3D 边界框）三类异构控制信号统一起来，实现对相机运动、对焦和构图的精确控制，同时保持时空一致性。实验表明，该方法在多种相机操作下均能生成可控且视觉一致的结果，在真实感和可编辑性上优于现有方法。
正文 · 原文
Abstract:We present Gen Through the Lens, a camera-controllable image-to-video generation framework that synthesizes videos from a given reference image while enabling realistic and physically consistent camera operations. Unlike previous models that treat camera motion as abstract conditioning or rely on a single coordinate system, our approach explicitly decomposes and fuses control signals across three coordinate spaces: the camera coordinate (modeled by intrinsic parameters), the world coordinate (represented by spatial geometry hints), and the object coordinate (described by 3D bounding boxes of target subjects). Through cross-coordinate conditioning fusion, these heterogeneous cues are unified to guide the generative process, enabling precise control of camera motion, focus, and framing while preserving temporal and spatial coherence. Extensive experiments demonstrate that our method produces controllable and visually consistent results across diverse camera operations, outperforming existing approaches in both realism and editability.
| Comments: | 15 pages, 9 figures, 5 tables. Shuai Li and Jinxu Xiang contributed equally; Ran Zhang is the corresponding author |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.15900 [cs.CV] |
| (or arXiv:2610.15900v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.15900 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ran Zhang [view email]
[v1]
Sun, 11 Oct 2026 20:27:58 UTC (6,919 KB)
来源：arXiv cs.AI · arxiv.org