UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models

2026-04-19

AI Summary

Existing camera-controllable image editing methods suffer from geometric drift and structural degradation under continuous camera motion due to fragmented geometric guidance and discrete viewpoint modeling. This work proposes a unified framework based on video diffusion models that jointly enhances geometric consistency across representation, architecture, and loss design. Specifically, it introduces a frame-decoupled geometric reference injection mechanism, a geometric anchor attention module, and a trajectory-endpoint geometric supervision strategy. The method achieves the first effective integration of multi-level continuous viewpoint priors, significantly outperforming current approaches on multiple public benchmarks while attaining state-of-the-art performance in both visual quality and geometric consistency.

Technology Category

Computer Vision: Diffusion Models for VisionMachine Learning: Multi-instance/Multi-view LearningKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Camera-controllable image editing aims to synthesize novel views of a given scene under varying camera poses while strictly preserving cross-view geometric consistency. However, existing methods typically rely on fragmented geometric guidance, such as only injecting point clouds at the representation level despite models containing multiple levels, and are mainly based on image diffusion models that operate on discrete view mappings. These two limitations jointly lead to geometric drift and structural degradation under continuous camera motion. We observe that while leveraging video models provides continuous viewpoint priors for camera-controllable image editing, they still struggle to form stable geometric understanding if geometric guidance remains fragmented. To systematically address this, we inject unified geometric guidance across three levels that jointly determine the generative output: representation, architecture, and loss function. To this end, we propose UniGeo, a novel camera-controllable editing framework. Specifically, at the representation level, UniGeo incorporates a frame-decoupled geometric reference injection mechanism to provide robust cross-view geometry context. At the architecture level, it introduces geometric anchor attention to align multi-view features. At the loss function level, it proposes a trajectory-endpoint geometric supervision strategy to explicitly reinforce the structural fidelity of target views. Comprehensive experiments across multiple public benchmarks, encompassing both extensive and limited camera motion settings, demonstrate that UniGeo significantly outperforms existing methods in both visual quality and geometric consistency.

Problem

• camera-controllable image editing
• geometric consistency
• geometric drift
• structural degradation
• continuous camera motion

Innovation

• geometric guidance unification
• camera-controllable image editing
• video diffusion models
• multi-view consistency
• trajectory-endpoint supervision