{"type":"ScholarlyArticle","title":"Bridging the Gap Between Gaussian Splatting and SLAM: A Geometric Gaussian Field-based Gaussian Splatting SLAM System","authors":[{"name":"Jiasheng He","slug":"jiasheng-he","given":"Jiasheng","family":"He","affiliation":""},{"name":"Wenbin Zhu","slug":"wenbin-zhu","given":"Wenbin","family":"Zhu","affiliation":""},{"name":"Xiaobin Liu","slug":"xiaobin-liu","given":"Xiaobin","family":"Liu","affiliation":""},{"name":"Jing Yuan","slug":"jing-yuan","given":"Jing","family":"Yuan","affiliation":""},{"name":"Yuhang Wei","slug":"yuhang-wei","given":"Yuhang","family":"Wei","affiliation":""}],"abstract":"Recent works in Gaussian Splatting (GS) SLAM highlight the importance of geometric structure. However, existing methods often rely on either 2D or 3D Gaussian primitives, lacking the balance between geometry and appearance, thus failing to precisely model spatial structures. Furthermore, current frameworks either solely utilize SLAM to provide poses for GS or optimize poses and all Gaussian parameters indiscriminately, which neglect geometric consistency constraints essential for robust localization, creating a gap between GS and SLAM. In this paper, a tight-coupling SLAM system based on a Geometric Gaussian Field (GGF) is proposed. First, GGF combines explicit spatial structures with implicit neural residuals to adaptively regulate the Gaussian morphologies, seamlessly transitioning between 2D and 3D Gaussian primitives, ensuring precise spatial modeling. Second, a Geometric Consistency-Guided Refinement (GCGR) strategy is introduced, which exploits depth and normal maps rendered by GGF to construct critical constraints for accurate pose estimation. Simultaneously, updated poses and spatial information are fed back to refine Gaussian morphology, establishing mutual enhancement and tight-coupling between GS and SLAM. Extensive experiments demonstrate that GGF-SLAM outperforms state-of-the-art methods in tracking accuracy, photorealistic rendering, and geometric reconstruction.","doi":"10.24963/ijcai.2026/130","url":"https://ijcai.org/proceedings/2026/130","pdf":"https://ijcai.org/proceedings/2026/0130.pdf","markdown":"https://ijcai.org/proceedings/2026/130.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/130","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":130,"pages":{"first":1161,"last":1169},"keywords":["Computer Vision: Machine learning for vision","Robotics: Localization, mapping, state estimation","Robotics: Perception","Robotics: Robotics and vision","Computer Vision: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}