{"type":"ScholarlyArticle","title":"IE-PMMA:Point Cloud Completion Through Inverse Edge-aware Upsampling and Precise Multi-Modal Feature Alignment","authors":[{"name":"Ran Jia","slug":"ran-jia","given":"Ran","family":"Jia","affiliation":""},{"name":"Junpeng Xue","slug":"junpeng-xue","given":"Junpeng","family":"Xue","affiliation":""},{"name":"Shuai Ma","slug":"shuai-ma","given":"Shuai","family":"Ma","affiliation":""},{"name":"Wenbo Lu","slug":"wenbo-lu","given":"Wenbo","family":"Lu","affiliation":""},{"name":"Kelei Wang","slug":"kelei-wang","given":"Kelei","family":"Wang","affiliation":""}],"abstract":"Point cloud completion is a crucial task in 3D computer vision. Multi-modal completion approaches have gained attention among the popular two-stage point cloud completion methods. However, there is a notable lack of research focused on accurately aligning data from different modalities within these methods. Additionally, in other point cloud-based tasks, edge point information often provides unexpected positive contributions. In this paper, we propose a novel point cloud completion method that leverages edge point information for the first time in the completion task, which also addresses the precise alignment of multi-modal data. In particular, we implement a two-step local-to-global module to achieve better alignment of multi-modal data during the preliminary point cloud generation process. Besides, we introduce a new spatial representation structure capable of extracting a fixed number of edge points. Moreover, with the assistance of edge information, we further design an inverse edge-aware upsampler to refine the point cloud. We evaluate our method on three typical datasets, and the results demonstrate that our IE-PMMA outperforms the existing state-of-the-art methods quantitatively and visually.","doi":"10.24963/ijcai.2025/138","url":"https://ijcai.org/proceedings/2025/138","pdf":"https://ijcai.org/proceedings/2025/0138.pdf","markdown":"https://ijcai.org/proceedings/2025/138.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/138","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":"Computer Vision","track":"Main Track","number":138,"pages":{"first":1233,"last":1241},"keywords":["Computer Vision: CV: Multimodal learning","Computer Vision: CV: 3D computer vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}