{"type":"ScholarlyArticle","title":"Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields","authors":[{"name":"Peng-Shuai Wang","slug":"peng-shuai-wang","given":"Peng-Shuai","family":"Wang","affiliation":""},{"name":"Yang Liu","slug":"yang-liu","given":"Yang","family":"Liu","affiliation":""},{"name":"Yu-Qi Yang","slug":"yu-qi-yang","given":"Yu-Qi","family":"Yang","affiliation":""},{"name":"Xin Tong","slug":"xin-tong","given":"Xin","family":"Tong","affiliation":""}],"abstract":"Multilayer perceptrons (MLPs) have been successfully used to represent 3D\r\nshapes implicitly and compactly, by mapping 3D coordinates to the\r\ncorresponding signed distance values or occupancy values. In this paper, we\r\npropose a novel positional encoding scheme, called Spline Positional\r\nEncoding, to map the input coordinates to a high dimensional space before\r\npassing them to MLPs, which help recover 3D signed distance fields with\r\nfine-scale geometric details from unorganized 3D point clouds.  We verified\r\nthe superiority of our approach over other positional encoding schemes on\r\ntasks of 3D shape reconstruction and 3D shape space learning from input\r\npoint clouds. The efficacy of our approach extended to image reconstruction\r\nis also demonstrated and evaluated.","doi":"10.24963/ijcai.2021/151","url":"https://ijcai.org/proceedings/2021/151","pdf":"https://ijcai.org/proceedings/2021/0151.pdf","markdown":"https://ijcai.org/proceedings/2021/151.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/151","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Computer Vision II","track":"Main Track","number":151,"pages":{"first":1091,"last":1097},"keywords":["Computer Vision: 2D and 3D Computer Vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}