CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modeling

2026-09-01

AI Summary

为解决图像编辑中相机参数控制问题，提出CameraEditor框架，将空间问题转化为时序预测任务，并通过动态全景裁剪和插入过渡帧等方法提高几何精度和内容一致性。

Abstract

Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent image editing models excel at semantic and stylistic manipulation, they struggle with explicit camera parameter control. When handling large perspective shifts, instruction-driven models face a dilemma: they either suffer from structural tearing or generate conservative outputs that ignore geometric instructions. To address this, we introduce CameraEditor, a framework that reformulates camera-controlled editing from a spatial problem into a temporal sequence prediction task. By leveraging the temporal coherence of video diffusion models, our approach integrates an explicit geometric perception module with a dynamic reference routing mechanism. This allows us to construct geometrically rigorous visual reference pairs via dynamic panorama cropping, overcoming the ambiguity of text-based instructions. Furthermore, CameraEditor strategically inserts intermediate transition frames to decompose large perspective shifts, providing a robust temporal buffer that preserves content identity and spatial coherence. We construct a training dataset of 5,760 instances. As an independent contribution, we introduce CamEditor-Bench, a model-agnostic evaluation suite of 462 test cases. Extensive experiments demonstrate that CameraEditor achieves state-of-the-art camera control precision and source identity preservation, outperforming existing methods.

Problem

• camera parameter control
• perspective shifts
• structural tearing
• geometric instructions

Innovation

• camera-controlled editing
• temporal sequence prediction
• geometric perception module
• dynamic reference routing
• intermediate transition frames