{"type":"ScholarlyArticle","title":"SmartSpatial: Enhancing 3D Spatial Awareness in Stable Diffusion with a Novel Evaluation Framework","authors":[{"name":"Mao Xun Huang","slug":"mao-xun-huang","given":"Mao Xun","family":"Huang","affiliation":""},{"name":"Brian J Chan","slug":"brian-j-chan","given":"Brian J","family":"Chan","affiliation":""},{"name":"Hen-Hsen Huang","slug":"hen-hsen-huang","given":"Hen-Hsen","family":"Huang","affiliation":""}],"abstract":"Stable Diffusion models have made remarkable strides in generating photorealistic images from text prompts but often falter when tasked with accurately representing complex spatial arrangements, particularly involving intricate 3D relationships. \r\nTo address this limitation, we introduce SmartSpatial, an innovative approach that not only enhances the spatial arrangement capabilities of Stable Diffusion but also fosters AI-assisted creative workflows through 3D-aware conditioning and attention-guided mechanisms. \r\nSmartSpatial incorporates depth information injection and cross-attention control to ensure precise object placement, delivering notable improvements in spatial accuracy metrics. \r\nIn conjunction with SmartSpatial, we present SmartSpatialEval, a comprehensive evaluation framework that bridges computational spatial accuracy with qualitative artistic assessments. \r\nExperimental results show that SmartSpatial significantly outperforms existing methods, setting new benchmarks for spatial fidelity in AI-driven art and creativity.","doi":"10.24963/ijcai.2025/1122","url":"https://ijcai.org/proceedings/2025/1122","pdf":"https://ijcai.org/proceedings/2025/1122.pdf","markdown":"https://ijcai.org/proceedings/2025/1122.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1122","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI, Arts & Creativity","track":"AI, Arts & Creativity","number":1122,"pages":{"first":10099,"last":10107},"keywords":["Theory and philosophy of arts and creativity in AI systems: Computational paradigms, architectures and models for creativity","Methods and resources: Machine learning, deep learning, neural models, reinforcement learning","Theory and philosophy of arts and creativity in AI systems: Evaluation and curation of artistic or creative artefacts","Application domains: Images, movies and visual arts"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}