{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T03:12:02Z","timestamp":1777518722556,"version":"3.51.4"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T00:00:00Z","timestamp":1734739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Point cloud data acquired through 3D scanning is frequently subject to fragmentation due to the constraints of the scanner\u2019s field of view and occlusions within the scanned object. The ensuing incompleteness in the data can significantly degrade the accuracy of subsequent computational tasks. Traditional methods for predicting complete point clouds from these fragments often fail to capture the fine-grained local details, leading to inaccurate reconstructions. In this work, we introduce a novel neural network architecture designed for point cloud completion that addresses these limitations.Our network accepts an incomplete point cloud and employs a multi-scale feature extraction module, which integrates an offset attention mechanism alongside a feature aggregation module operating across various scales. This dual approach significantly bolsters the network\u2019s capacity to discern both local and global features inherent in the point cloud data. Furthermore, we incorporate a seed generation module within our missing point cloud generator, harnessing a hierarchical feature pyramid network to forecast the entirety of the point cloud. This innovative strategy allows our network to accurately predict the structure of missing regions.Empirical evaluations conducted on the Shapenet-Part and ModelNet10 datasets substantiate the efficacy of our proposed methodology. Our approach outperforms the state-of-the-art PF-Net\u00a0algorithm, achieving a remarkable reduction in chamfer distance by 16.15$\\%$ and 41.87$\\%$ on the respective datasets. Visual inspection of the results underscores the robust generalization capabilities of our algorithm, which is particularly evident in scenarios with limited dataset sizes. It adeptly predicts the contours of the missing regions and synthesizes a more comprehensive point cloud shape.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae135","type":"journal-article","created":{"date-parts":[[2024,12,22]],"date-time":"2024-12-22T09:41:18Z","timestamp":1734860478000},"page":"605-616","source":"Crossref","is-referenced-by-count":1,"title":["Offset attention with seed generation for point cloud completion"],"prefix":"10.1093","volume":"68","author":[{"given":"Yuke","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology , Chongqing 400054 ,","place":["China"]},{"name":"Smart Transportation College , Chongqing Vocational College of Public Transportation, Chongqing ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology , Chongqing 400054 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chongqing University of Technology , Chongqing 400054 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,12,21]]},"reference":[{"key":"2025062421083746200_ref1","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep learning for 3D point clouds: a survey","volume":"43","author":"Guo","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025062421083746200_ref2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cad.2017.07.005","article-title":"Urban building reconstruction from raw lidar point data","volume":"93","author":"Yi","year":"2017","journal-title":"Comput-Aided Des"},{"key":"2025062421083746200_ref3","first-page":"652","article-title":"PointNet: deep learning on point sets for 3D classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"2025062421083746200_ref4","first-page":"6799","article-title":"PointCNN: convolution on x-transformed points","volume":"31","author":"Li","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025062421083746200_ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","journal-title":"ACM Trans Graph"},{"key":"2025062421083746200_ref6","first-page":"206","article-title":"FoldingNet: point cloud auto-encoder via deep grid deformation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Yang","year":"2019"},{"key":"2025062421083746200_ref7","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"PCT: point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Computational Visual Media"},{"key":"2025062421083746200_ref8","first-page":"10266","article-title":"Learning progressive point embeddings for 3D point cloud generation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wen","year":"2021"},{"key":"2025062421083746200_ref9","first-page":"8524","article-title":"Variational relational point completion network","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Pan"},{"key":"2025062421083746200_ref10","first-page":"7443","article-title":"PMP-Net: point cloud completion by learning multi-step point moving paths","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Wen"},{"key":"2025062421083746200_ref11","first-page":"9782","article-title":"Unsupervised point cloud pre-training via occlusion completion","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Wang"},{"key":"2025062421083746200_ref12","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-030-42227-1_5","article-title":"Multi-layer perceptrons","volume-title":"Computational Intelligence: A Methodological Introduction","author":"Kruse"},{"key":"2025062421083746200_ref13","article-title":"PointNet++: deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025062421083746200_ref14","first-page":"7662","article-title":"PF-Net: point fractal network for 3D point cloud completion","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Huang"},{"key":"2025062421083746200_ref15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","article-title":"Generative adversarial networks: an overview","volume":"35","author":"Creswell","year":"2018","journal-title":"IEEE Signal Process Mag"},{"key":"2025062421083746200_ref16","first-page":"6871","article-title":"A point sampling algorithm for 3D matching of irregular geometries","volume-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Birdal","year":"2018"},{"key":"2025062421083746200_ref17","article-title":"Attention is all you need","volume":"30","author":"Vaswani","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025062421083746200_ref18","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"International conference on machine learning","author":"Achlioptas"},{"key":"2025062421083746200_ref19","first-page":"2117","article-title":"Feature pyramid networks for object detection","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Lin"},{"key":"2025062421083746200_ref20","first-page":"5499","article-title":"SnowflakeNet: point cloud completion by snowflake point deconvolution with skip-transformer","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Xiang"},{"key":"2025062421083746200_ref21","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-031-20062-5_24","article-title":"SeedFormer: patch seeds based point cloud completion with upsample transformer","author":"Zhou","year":"2022","journal-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part III"},{"key":"2025062421083746200_ref22","article-title":"ResNet in ResNet: generalizing residual architectures","author":"Targ"},{"key":"2025062421083746200_ref23","article-title":"Rethinking network design and local geometry in point cloud: a simple residual MLP framework","author":"Ma"},{"key":"2025062421083746200_ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980238","article-title":"A scalable active framework for region annotation in 3D shape collections","volume":"35","author":"Yi","year":"2016","journal-title":"ACM Ser Comput Methodol"},{"key":"2025062421083746200_ref25","article-title":"Shapenet: an information-rich 3D model repository","author":"Chang"},{"key":"2025062421083746200_ref26","first-page":"1912","article-title":"3D ShapeNets: a deep representation for volumetric shapes","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wu","year":"2016"},{"key":"2025062421083746200_ref27","first-page":"1009","article-title":"3D point capsule networks","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Zhao"},{"key":"2025062421083746200_ref28","doi-asserted-by":"publisher","first-page":"538","DOI":"10.11834\/jig.210510","article-title":"Multi-scale transformer based point cloud completion network","volume":"27","author":"Liu","year":"2022","journal-title":"J Image Graph"},{"key":"2025062421083746200_ref29","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.neucom.2022.08.007","article-title":"Cosmos propagation network: deep learning model for point cloud completion","volume":"507","author":"Lin","year":"2022","journal-title":"Neurocomputing"},{"key":"2025062421083746200_ref30","first-page":"24","article-title":"Point cloud completion algorithm based on multi-stage fractal combination","volume":"1","author":"Zeng","year":"2022","journal-title":"Computer and Modernization"},{"key":"2025062421083746200_ref31","first-page":"292","article-title":"Multi-scale point cloud completion network","volume":"18","author":"Li","journal-title":"China Sciencepaper"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/605\/61251622\/bxae135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/605\/61251622\/bxae135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T01:08:49Z","timestamp":1750813729000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/6\/605\/7930080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,21]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,12,21]]},"published-print":{"date-parts":[[2025,6,12]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae135","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2024,12,21]]}}}