{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T06:27:35Z","timestamp":1791872855760,"version":"4.3.4"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Three-dimensional (3D) point clouds acquired by LiDAR are fundamental for applications such as autonomous navigation, mobile robotics, infrastructure inspection, and cultural-heritage documentation. However, environmental disturbances and sensor limitations often yield incomplete or noisy point clouds, degrading downstream performance. This study addresses robust, high-fidelity point cloud completion under such practical conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an unsupervised deep learning framework, Multi-Resolution Completion Net (MRC-Net), which builds on ShapeInversion by integrating a Generative Adversarial Network (GAN) inversion strategy with multi-resolution principles. The architecture comprises an encoder for feature extraction, a generator for completion, and a discriminator to assess geometric integrity and detail. Two key designs enable strong performance without supervision: (i) a multi-resolution degradation mechanism that guides reconstruction across coarse-to-fine scales, and (ii) a multi-scale discriminator that captures both global structure and local details.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Extensive experiments on multiple datasets demonstrate that MRC-Net achieves accuracy comparable to leading supervised approaches. On virtual datasets (e.g., CRN), MRC-Net attains an average Chamfer Distance (CD) of 8.0 and an F1 score of 91.3. On a custom dataset targeting agricultural scenarios, the model preserves object integrity across varying complexity: for regular cartons, it achieves CD 3.3 and F1 97.3; for structurally complex simulated plants, it maintains overall shape while delivering average CD 8.6 and F1 88.1.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results indicate that MRC-Net advances unsupervised point cloud completion by balancing global shape consistency with fine-grained detail. The method provides a reliable data foundation for downstream tasks\u2014including autonomous navigation, high-precision 3D modeling, and agricultural robotics\u2014thereby contributing to improved data quality in precision-agriculture and related domains.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2025.1698843","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:25:52Z","timestamp":1766125552000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Structure-aware completion of plant 3D LiDAR point clouds via a multi-resolution GAN-inversion network"],"prefix":"10.3389","volume":"16","author":[{"given":"Zhiming","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yitian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinglong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingxin","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoju","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengguo","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"112265","DOI":"10.1016\/j.sna.2020.112265","article-title":"Different sensor based intelligent spraying systems in Agriculture","volume":"316","author":"Abbas","year":"2020","journal-title":"Sensors Actuators A: Phys"},{"key":"B2","first-page":"40","article-title":"Learning representations and generative models for 3d point clouds","volume-title":"International conference on machine learning","author":"Achlioptas","year":"2018"},{"key":"B3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.compag.2012.12.012","article-title":"Potential of a terrestrial LiDAR-based system to characterise weed vegetation in maize crops","volume":"92","author":"And\u00fajar","year":"2013","journal-title":"Comput. Electron. Agric"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1709.06158","article-title":"Matterport3d: Learning from rgb-d data in indoor environments","author":"Chang","year":"2017","journal-title":"arXiv preprint arXiv:1709.06158"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.00069","article-title":"Unpaired point cloud completion on real scans using adversarial training","author":"Chen","year":"2019","journal-title":"arXiv preprint arXiv:1904.00069"},{"key":"B6","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1007\/978-3-319-46484-8_38","article-title":"3d-r2n2: A unified approach for single and multi-view 3d object reconstruction","volume-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14","author":"Choy","year":"2016"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.808484","article-title":"Trend technologies for robotic fertilization process in row crops","volume":"9","author":"Cruz Ulloa","year":"2022","journal-title":"Front. Robotics AI"},{"key":"B8","first-page":"5828","article-title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","author":"Dai","year":"2017"},{"key":"B9","first-page":"5868","article-title":"Shape completion using 3d-encoder-predictor cnns and shape synthesis","author":"Dai","year":"2017"},{"key":"B10","first-page":"4578","article-title":"Scancomplete: Large-scale scene completion and semantic segmentation for 3d scans","author":"Dai","year":"2018"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.01673","article-title":"Generative multi-adversarial networks","author":"Durugkar","year":"2016","journal-title":"arXiv preprint arXiv:1611.01673"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.5555\/2969033.2969091","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume":"27","author":"Eigen","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.21273\/HORTSCI16157-21","article-title":"Reducing the nursery pesticide footprint with laser-guided, variable-rate spray application technology","volume":"56","author":"Fessler","year":"2021","journal-title":"HortScience"},{"key":"B14","doi-asserted-by":"crossref","first-page":"3354","DOI":"10.1109\/CVPR.2012.6248074","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","volume-title":"2012 IEEE conference on computer vision and pattern recognition","author":"Geiger","year":"2012"},{"key":"B15","doi-asserted-by":"publisher","first-page":"927","DOI":"10.13031\/aea.14201","article-title":"Research progress on variable-rate spraying technology in orchards","volume":"36","author":"Gu","year":"2020","journal-title":"Appl. Eng. Agric"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2025.101017","article-title":"SASP: Segment any strawberry plant, an end-to-end strawberry canopy volume estimation","volume":"11","author":"Huang","year":"2025","journal-title":"Smart Agric. Technol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.06814","article-title":"ComPC: completing a 3D point cloud with 2D diffusion priors","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv:2404.06814"},{"key":"B18","first-page":"7662","article-title":"Pf-net: Point fractal network for 3d point cloud completion","author":"Huang","year":"2020"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2023.1087239","article-title":"The effects of sampling and instrument orientation on LiDAR data from crop plots","volume":"14","author":"Khorsandi","year":"2023","journal-title":"Front. Plant Sci"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.02671","article-title":"Unsupervised point cloud completion through unbalanced optimal transport","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv:2410.02671"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1510683","article-title":"An autonomous navigation method for orchard mobile robots based on octree 3D point cloud optimization","volume":"15","author":"Li","year":"2025","journal-title":"Front. Plant Sci"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.1024360","article-title":"Inter-row information recognition of maize in the middle and late stages via LiDAR supplementary vision","volume":"13","author":"Li","year":"2022","journal-title":"Front. Plant Sci"},{"key":"B23","first-page":"5066","article-title":"Dapointr: Domain adaptive point transformer for point cloud completion","author":"Li","year":"2025"},{"key":"B24","doi-asserted-by":"publisher","first-page":"4077","DOI":"10.1109\/TMM.2021.3113786","article-title":"Anigan: Style-guided generative adversarial networks for unsupervised anime face generation","volume":"24","author":"Li","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"key":"B25","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B26","first-page":"11596","article-title":"Morphing and sampling network for dense point cloud completion","author":"Liu","year":"2020"},{"key":"B27","first-page":"909","article-title":"Partnet: A large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding","author":"Mo","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","first-page":"7474","DOI":"10.1109\/TPAMI.2021.3115428","article-title":"Exploiting deep generative prior for versatile image restoration and manipulation","volume":"44","author":"Pan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B29","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Qi","year":"2017"},{"key":"B30","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/CVPR.2017.16","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Qi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1491170","article-title":"Plant stem and leaf segmentation and phenotypic parameter extraction using neural radiance fields and lightweight point cloud segmentation networks","volume":"16","author":"Qiao","year":"2025","journal-title":"Front. Plant Sci"},{"key":"B32","first-page":"5898","article-title":"Rl-gan-net: A reinforcement learning agent controlled gan network for real-time point cloud shape completion","author":"Sarmad","year":"2019"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2024.1474797","article-title":"Outdoor large-scene 3D point cloud reconstruction based on transformer","volume":"12","author":"Tang","year":"2024","journal-title":"Front. Phys"},{"key":"B34","first-page":"383","article-title":"Topnet: Structural point cloud decoder","author":"Tchapmi","year":"2019"},{"key":"B35","first-page":"790","article-title":"Cascaded refinement network for point cloud completion","author":"Wang","year":"2020"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1616611","article-title":"BranchMatch: point cloud registration for individual apple trees with limited overlap based on local structure characteristics","volume":"16","author":"Wang","year":"2025","journal-title":"Front. Plant Sci"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.3390\/agronomy13041077","article-title":"Calculation method of canopy dynamic meshing division volumes for precision pesticide application in orchards based on liDAR","volume":"13","author":"Wang","year":"2023","journal-title":"Agronomy"},{"key":"B38","doi-asserted-by":"publisher","first-page":"172","DOI":"10.25165\/j.ijabe.20221505.7830","article-title":"Maize (Zea mays L.) seedling detection based on the fusion of a modified deep learning model and a novel Lidar points projecting strategy","volume":"15","author":"Wang","year":"2022","journal-title":"Int. J. Agric. Biol. Eng"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1642388","article-title":"Accurate plant 3D reconstruction and phenotypic traits extraction via stereo imaging and multi-view point cloud alignment","volume":"16","author":"Wang","year":"2025","journal-title":"Front. Plant Sci"},{"key":"B40","first-page":"27243","article-title":"Pcdreamer: Point cloud completion through multi-view diffusion priors","author":"Wei","year":"2025"},{"key":"B41","first-page":"365","article-title":"Grnet: Gridding residual network for dense point cloud completion","volume-title":"European Conference on Computer Vision","author":"Xie","year":"2020"},{"key":"B42","first-page":"6239","article-title":"Shapeformer: Transformer-based shape completion via sparse representation","author":"Yan","year":"2022"},{"key":"B43","first-page":"679","article-title":"3d object reconstruction from a single depth view with adversarial learning","author":"Yang","year":"2017"},{"key":"B44","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1109\/3DV.2018.00088","article-title":"Pcn: Point completion network","volume-title":"2018 international conference on 3D vision (3DV)","author":"Yuan","year":"2018"},{"key":"B45","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.biosystemseng.2020.05.015","article-title":"Semantic segmentation of sparse 3D point cloud based on geometrical features for trellis-structured apple orchard","volume":"196","author":"Zeng","year":"2020","journal-title":"Biosyst. Eng"},{"key":"B46","first-page":"1768","article-title":"Unsupervised 3d shape completion through gan inversion","author":"Zhang","year":"2021"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2408.14846","article-title":"Diffusion-occ: 3D point cloud completion via occupancy diffusion","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2408.14846"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.13031\/ja.15285","article-title":"Static and dynamic performance evaluation of a solid-state liDAR for 3D object detection in greenhouse spray applications","volume":"66","author":"Zhang","year":"2023","journal-title":"J. ASABE"},{"key":"B49","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1007\/978-3-030-58595-2_31","article-title":"Detail preserved point cloud completion via separated feature aggregation","volume-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16","author":"Zhang","year":"2020"},{"key":"B50","doi-asserted-by":"publisher","first-page":"154","DOI":"10.25165\/j.ijabe.20201303.5460","article-title":"Automatic sweet pepper detection based on point cloud images using subtractive clustering","volume":"13","author":"Zhao","year":"2020","journal-title":"Int. J. Agric. Biol. Eng"},{"key":"B51","doi-asserted-by":"publisher","first-page":"106131","DOI":"10.1016\/j.compag.2021.106131","article-title":"A fertilizer discharge detection system based on point cloud data and an efficient volume conversion algorithm","volume":"185","author":"Zhao","year":"2021","journal-title":"Comput. Electron. Agric"},{"key":"B52","doi-asserted-by":"publisher","first-page":"337","DOI":"10.13031\/trans.12020","article-title":"Validation of a laser-guided variable-rate sprayer for managing insects in ornamental nurseries","volume":"60","author":"Zhu","year":"2017","journal-title":"Trans. ASABE"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1698843\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T06:25:55Z","timestamp":1766125555000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1698843\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":52,"alternative-id":["10.3389\/fpls.2025.1698843"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1698843","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"article-number":"1698843"}}