PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing

TL;DR

PhyEdit introduces a 3D-aware image editing framework that improves physical accuracy and consistency in object manipulation by integrating explicit geometric simulation and a new dataset.

Contribution

The paper presents PhyEdit, a novel image editing method combining geometric simulation with supervision, and introduces RealManip-10K and ManipEval for evaluation.

Findings

Outperforms existing methods in 3D geometric accuracy.

Achieves more consistent and physically accurate object manipulations.

Demonstrates effectiveness on real-world images with depth annotations.

Abstract

Achieving physically accurate object manipulation in image editing is essential for its potential applications in interactive world models. However, existing visual generative models often fail at precise spatial manipulation, resulting in incorrect scaling and positioning of objects. This limitation primarily stems from the lack of explicit mechanisms to incorporate 3D geometry and perspective projection. To achieve accurate manipulation, we develop PhyEdit, an image editing framework that leverages explicit geometric simulation as contextual 3D-aware visual guidance. By combining this plug-and-play 3D prior with joint 2D--3D supervision, our method effectively improves physical accuracy and manipulation consistency. To support this method and evaluate performance, we present a real-world dataset, RealManip-10K, for 3D-aware object manipulation featuring paired images and depth annotations. We also propose ManipEval, a benchmark with multi-dimensional metrics to evaluate 3D spatial control and geometric consistency. Extensive experiments show that our approach outperforms existing methods, including strong closed-source models, in both 3D geometric accuracy and manipulation consistency.