{"type":"ScholarlyArticle","title":"PointGP: Geometry-Primed Attention for Point Cloud Analysis","authors":[{"name":"Yong Yang","slug":"yong-yang","given":"Yong","family":"Yang","affiliation":""},{"name":"Jianming Huang","slug":"jianming-huang","given":"Jianming","family":"Huang","affiliation":""},{"name":"Mengyuan Ge","slug":"mengyuan-ge","given":"Mengyuan","family":"Ge","affiliation":""},{"name":"Chunyang Huang","slug":"chunyang-huang","given":"Chunyang","family":"Huang","affiliation":""},{"name":"Bingbing Hu","slug":"bingbing-hu","given":"Bingbing","family":"Hu","affiliation":""},{"name":"Junfeng Yao","slug":"junfeng-yao","given":"Junfeng","family":"Yao","affiliation":""}],"abstract":"Transformer-based architectures have demonstrated strong performance in 3D point cloud understanding, yet many existing methods generate attention weights mainly from semantic feature similarity. In deep networks, feature-centric attention may become less selective as point features are progressively smoothed, a behavior associated with feature homogenization and rank collapse, which can weaken the structural discrimination of local aggregation.We propose PointGP, a geometry-primed framework that uses rectified local geometric topology as the primary cue for attention generation. PointGP introduces a Semantic-Guided Manifold Rectifier to predict feature-conditioned local coordinate offsets, and a Dual-Stream Geometric Kernel to compute attention logits from both raw and rectified geometric cues. By reducing reliance on explicit query-key feature matching while implicitly incorporating semantic guidance through geometric rectification, PointGP provides an effective and efficient mechanism for local point aggregation.Experiments across five benchmarks covering classification, part segmentation, and indoor scene segmentation show that PointGP achieves competitive accuracy with strong parameter and computational efficiency compared with representative strong baselines.","doi":"10.24963/ijcai.2026/222","url":"https://ijcai.org/proceedings/2026/222","pdf":"https://ijcai.org/proceedings/2026/0222.pdf","markdown":"https://ijcai.org/proceedings/2026/222.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/222","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":222,"pages":{"first":1992,"last":2000},"keywords":["Computer Vision: Scene analysis and understanding","Computer Vision: Machine learning for vision","Computer Vision: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}