{"ID":2888248,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.23300","arxiv_id":"2507.23300","title":"Training-free Geometric Image Editing on Diffusion Models","abstract":"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","short_abstract":"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 o...","url_abs":"https://arxiv.org/abs/2507.23300","url_pdf":"https://arxiv.org/pdf/2507.23300v2","authors":"[\"Hanshen Zhu\",\"Zhen Zhu\",\"Kaile Zhang\",\"Yiming Gong\",\"Yuliang Liu\",\"Xiang Bai\"]","published":"2025-07-31T07:36:00Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611520,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2888248,"paper_url":"https://arxiv.org/abs/2507.23300","paper_title":"Training-free Geometric Image Editing on Diffusion Models","repo_url":"https://github.com/CIawevy/FreeFine","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}