From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors
This addresses the challenge of realistic physics-aware editing for users in computer vision and graphics, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of generating physically plausible results in instruction-based image editing for complex causal dynamics like refraction or material deformation, achieving a 5.9% improvement in physical realism and 10.1% in knowledge-grounded editing over Qwen-Image-Edit.
Instruction-based image editing has achieved remarkable success in semantic alignment, yet state-of-the-art models frequently fail to render physically plausible results when editing involves complex causal dynamics, such as refraction or material deformation. We attribute this limitation to the dominant paradigm that treats editing as a discrete mapping between image pairs, which provides only boundary conditions and leaves transition dynamics underspecified. To address this, we reformulate physics-aware editing as predictive physical state transitions and introduce PhysicTran38K, a large-scale video-based dataset comprising 38K transition trajectories across five physical domains, constructed via a two-stage filtering and constraint-aware annotation pipeline. Building on this supervision, we propose PhysicEdit, an end-to-end framework equipped with a textual-visual dual-thinking mechanism. It combines a frozen Qwen2.5-VL for physically grounded reasoning with learnable transition queries that provide timestep-adaptive visual guidance to a diffusion backbone. Experiments show that PhysicEdit improves over Qwen-Image-Edit by 5.9% in physical realism and 10.1% in knowledge-grounded editing, setting a new state-of-the-art for open-source methods, while remaining competitive with leading proprietary models.