Training-free Geometric Image Editing on Diffusion Models
This work addresses geometric image editing for users needing precise object manipulations in images, representing an incremental improvement over existing diffusion-based methods.
The paper tackles geometric image editing by repositioning, reorienting, or reshaping objects in images while maintaining scene coherence, proposing a decoupled pipeline that separates object transformation, inpainting, and refinement using a training-free diffusion method called FreeFine, and it outperforms state-of-the-art alternatives in image fidelity and edit precision on the new GeoBench benchmark.
We tackle the task of geometric image editing, where an object within an image is repositioned, reoriented, or reshaped while preserving overall scene coherence. Previous diffusion-based editing methods often attempt to handle all relevant subtasks in a single step, proving difficult when transformations become large or structurally complex. We address this by proposing a decoupled pipeline that separates object transformation, source region inpainting, and target region refinement. Both inpainting and refinement are implemented using a training-free diffusion approach, FreeFine. In experiments on our new GeoBench benchmark, which contains both 2D and 3D editing scenarios, FreeFine outperforms state-of-the-art alternatives in image fidelity, and edit precision, especially under demanding transformations. Code and benchmark are available at: https://github.com/CIawevy/FreeFine