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
@article{arxiv.2507.23300,
title = {Training-free Geometric Image Editing on Diffusion Models},
author = {Hanshen Zhu and Zhen Zhu and Kaile Zhang and Yiming Gong and Yuliang Liu and Xiang Bai},
journal= {arXiv preprint arXiv:2507.23300},
year = {2025}
}