{"ID":2884011,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07135","arxiv_id":"2508.07135","title":"Canvas3D: Empowering Precise Spatial Control for Image Generation with Constraints from a 3D Virtual Canvas","abstract":"Generative AI (GenAI) has significantly advanced the ease and flexibility of image creation. However, it remains a challenge to precisely control spatial compositions, including object arrangement and scene conditions. To bridge this gap, we propose Canvas3D, an interactive system leveraging a 3D engine to enable precise spatial manipulation for image generation. Upon user prompt, Canvas3D automatically converts textual descriptions into interactive objects within a 3D engine-driven virtual canvas, empowering direct and precise spatial configuration. These user-defined arrangements generate explicit spatial constraints that guide generative models in accurately reflecting user intentions in the resulting images. We conducted a closed-end comparative study between Canvas3D and a baseline system. And an open-ended study to evaluate our system \"in the wild\". The result indicates that Canvas3D outperforms the baseline on spatial control, interactivity, and overall user experience.","short_abstract":"Generative AI (GenAI) has significantly advanced the ease and flexibility of image creation. However, it remains a challenge to precisely control spatial compositions, including object arrangement and scene conditions. To bridge this gap, we propose Canvas3D, an interactive system leveraging a 3D engine to enable preci...","url_abs":"https://arxiv.org/abs/2508.07135","url_pdf":"https://arxiv.org/pdf/2508.07135v1","authors":"[\"Runlin Duan\",\"Yuzhao Chen\",\"Rahul Jain\",\"Yichen Hu\",\"Jingyu Shi\",\"Karthik Ramani\"]","published":"2025-08-10T01:15:37Z","proceeding":"cs.HC","tasks":"[\"cs.HC\"]","methods":"[]","has_code":false}