{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:17:56Z","timestamp":1778285876615,"version":"3.51.4"},"reference-count":47,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":139,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>With generative AI technologies advancing rapidly, the capabilities for 3D model generation and transformation are expanding across industries like manufacturing, healthcare, and virtual reality. However, existing methods based on generative adversarial networks (GANs), autoencoders, or transformers still have notable limitations. They primarily generate entire objects without providing flexibility for independent part transformation or precise control over model components. These constraints pose challenges for applications requiring complex object manipulation and fine\u2010grained adjustments. To overcome these limitations, we propose PartConverter, a novel part\u2010oriented point cloud transformation framework emphasizing flexibility and precision in 3D model transformations. PartConverter leverages attention mechanisms and autoencoders to capture crucial details within each part while modeling the relationships between components, thereby enabling highly customizable, part\u2010wise transformations that maintain overall consistency. Additionally, our part assembler ensures that transformed parts align coherently, resulting in a consistent and realistic final 3D shape. This framework significantly enhances control over detailed part modeling, increasing the flexibility and efficiency of 3D model transformation workflows.<\/jats:p>","DOI":"10.1049\/ipr2.70104","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T02:16:02Z","timestamp":1747793762000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PartConverter: A Part\u2010Oriented Transformation Framework for Point Clouds"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3145-689X","authenticated-orcid":false,"given":"Sheng\u2010Yun","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering National Kaohsiung University of Science and Technology  Kaohsiung City Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8875-678X","authenticated-orcid":false,"given":"Tyng\u2010Yeu","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering National Kaohsiung University of Science and Technology  Kaohsiung City Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.destud.2019.11.003"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14104112"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mtbio.2023.100792"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering4040079"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.destud.2021.101046"},{"key":"e_1_2_10_7_1","unstructured":"IKEA Global \u201cLaunch of new IKEA Place app\u2014IKEA Global \u201d accessed December 2023 https:\/\/www.ikea.com\/global\/en\/newsroom\/innovation\/ikea\u2010launches\u2010ikea\u2010place\u2010a\u2010new\u2010app\u2010that\u2010allows\u2010people\u2010to\u2010virtually\u2010place\u2010furniture\u2010in\u2010their\u2010home\u2010170912\/."},{"key":"e_1_2_10_8_1","unstructured":"I.Goodfellow J.Pouget\u2010Abadie M.Mirza et\u00a0al. \u201cGenerative Adversarial Nets \u201d inAdvances in Neural Information Processing Systems(Curran Associates Inc. 2014)."},{"key":"e_1_2_10_9_1","unstructured":"J.Wu C.Zhang T.Xue B.Freeman andJ.Tenenbaum \u201cLearning a Probabilistic Latent Space of Object Shapes via 3D Generative\u2010Adversarial Modeling \u201d inAdvances in Neural Information Processing Systems(Curran Associates Inc. 2016)."},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356494"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"Q.Chen J.Merz A.Sanghi H.Shayani A.Mahdavi\u2010Amiri andH.Zhang \u201cUNIST: Unpaired Neural Implicit Shape Translation Network \u201d in2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2022) 18593\u201318601.","DOI":"10.1109\/CVPR52688.2022.01806"},{"key":"e_1_2_10_12_1","unstructured":"C.Jiang J.Huang A.Tagliasacchi andL. J.Guibas \u201cShapeFlow: Learnable Deformation Flows Among 3D Shapes \u201d inAdvances in Neural Information Processing Systems(Curran Associates Inc. 2020) 9745\u20139757."},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"G.Yang X.Huang Z.Hao M.\u2010Y.Liu S.Belongie andB.Hariharan \u201cPointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows \u201d in2019 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 4540\u20134549.","DOI":"10.1109\/ICCV.2019.00464"},{"key":"e_1_2_10_14_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et\u00a0al. \u201cAttention Is All You Need \u201d inAdvances in Neural Information Processing Systems(Curran Associates Inc. 2017)."},{"key":"e_1_2_10_15_1","doi-asserted-by":"crossref","unstructured":"Y.Sun Y.Wang Z.Liu J. E.Siegel andS. E.Sarma \u201cPointGrow: Autoregressively Learned Point Cloud Generation With Self\u2010Attention \u201d in2020 IEEE Winter Conference on Applications of Computer Vision (WACV)(IEEE 2020) 61\u201370.","DOI":"10.1109\/WACV45572.2020.9093430"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"K.Mo S.Zhu A. X.Chang et\u00a0al. \u201cPartNet: A Large\u2010Scale Benchmark for Fine\u2010Grained and Hierarchical Part\u2010Level 3D Object Understanding \u201d in2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2019) 909\u2013918.","DOI":"10.1109\/CVPR.2019.00100"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356527"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2021.02.006"},{"key":"e_1_2_10_19_1","unstructured":"N.Parmar A.Vaswani J.Uszkoreit et\u00a0al. \u201cImage Transformer \u201d inProceedings of the 35th International Conference on Machine Learning(PMLR 2018) 4055\u20134064."},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"Z.Yi H.Zhang P.Tan andM.Gong \u201cDualGAN: Unsupervised Dual Learning for Image\u2010to\u2010Image Translation \u201d in2017 IEEE International Conference on Computer Vision (ICCV)(IEEE 2017) 2868\u20132876.","DOI":"10.1109\/ICCV.2017.310"},{"key":"e_1_2_10_21_1","doi-asserted-by":"crossref","unstructured":"P.Isola J.\u2010Y.Zhu T.Zhou andA. A.Efros \u201cImage\u2010to\u2010Image Translation With Conditional Adversarial Networks \u201d in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2017) 5967\u20135976.","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_2_10_22_1","unstructured":"M.\u2010Y.Liu T.Breuel andJ.Kautz \u201cUnsupervised Image\u2010to\u2010Image Translation Networks \u201d inProceedings of the 31st International Conference on Neural Information Processing Systems(Curran Associates Inc. 2017) 700\u2013708."},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_2_10_24_1","unstructured":"P.Achlioptas O.Diamanti I.Mitliagkas andL.Guibas \u201cLearning Representations and Generative Models for 3D Point Clouds \u201d inProceedings of the 35th International Conference on Machine Learning(PMLR 2018) 40\u201349."},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6798"},{"key":"e_1_2_10_26_1","unstructured":"M.Segu M.Grinvald R.Siegwart andF.Tombari \u201c3DSNet: Unsupervised Shape\u2010to\u2010Shape 3D Style Transfer \u201d arXiv:2011.13388 (2021)."},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"K.Zhang Y.Chen X.Yang W.Zhang andC.Jin \u201cPoint Cloud Part Editing: Segmentation Generation Assembly and Selection \u201d inProceedings of the Thirty\u2010Eighth AAAI Conference on Artificial Intelligence and Thirty\u2010Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'24\/IAAI'24\/EAAI'24) Vol.38(AAAI Press 2024) 7187\u20137195.","DOI":"10.1609\/aaai.v38i7.28547"},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","unstructured":"X.Liu Z.Han X.Wen Y.\u2010S.Liu andM.Zwicker \u201cL2G Auto\u2010Encoder: Understanding Point Clouds by Local\u2010to\u2010Global Reconstruction With Hierarchical Self\u2010Attention \u201d inProceedings of the 27th ACM International Conference on Multimedia(Association for Computing Machinery 2019) 989\u2013997.","DOI":"10.1145\/3343031.3350960"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943235"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16163045"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"C.Wu J.Zheng J.Pfrommer andJ.Beyerer \u201cAttention\u2010based Part Assembly for 3D Volumetric Shape Modeling \u201d in2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(IEEE 2023) 2717\u20132726.","DOI":"10.1109\/CVPRW59228.2023.00272"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"J.Zhou X.Wen B.Ma et\u00a0al. \u201c3D\u2010OAE: Occlusion Auto\u2010Encoders for Self\u2010Supervised Learning on Point Clouds \u201d in2024 IEEE International Conference on Robotics and Automation (ICRA)(IEEE 2024) 15416\u201315423.","DOI":"10.1109\/ICRA57147.2024.10610588"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"R.Wu Y.Zhuang K.Xu H.Zhang andB.Chen \u201cPQ\u2010NET: A Generative Part Seq2Seq Network for 3D Shapes \u201d in2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 826\u2013835.","DOI":"10.1109\/CVPR42600.2020.00091"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","unstructured":"Y.LiandG.Baciu \u201cSAPCGAN: Self\u2010Attention Based Generative Adversarial Network for Point Clouds \u201d in2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)(IEEE 2020) 52\u201359.","DOI":"10.1109\/ICCICC50026.2020.9450255"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3585508"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"K.Nakayama M.Angelina Uy J.Huang S.\u2010M.Hu K.Li andL. J.Guibas \u201cDiffFacto: Controllable Part\u2010Based 3D Point Cloud Generation With Cross Diffusion \u201d August 20 2023 https:\/\/doi.org\/10.48550\/arXiv.2305.01921.","DOI":"10.1109\/ICCV51070.2023.01311"},{"key":"e_1_2_10_37_1","unstructured":"S.Li D.Paschalidou andL.Guibas \u201cPASTA: Controllable Part\u2010Aware Shape Generation with Autoregressive Transformers \u201d July 18 2024 https:\/\/doi.org\/10.48550\/arXiv.2407.13677."},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"M.Chen R.Shapovalov I.Laina et\u00a0al. \u201cPartGen: Part\u2010Level 3D Generation and Reconstruction With Multi\u2010View Diffusion Models \u201d December 29 2024 https:\/\/doi.org\/10.48550\/arXiv.2412.18608.","DOI":"10.1109\/CVPR52734.2025.00552"},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","unstructured":"K.Tertikas D.Paschalidou B.Pan et\u00a0al. \u201cPartNeRF: Generating Part\u2010Aware Editable 3D Shapes Without 3D Supervision \u201d March 21 2023 https:\/\/doi.org\/10.48550\/arXiv.2303.09554.","DOI":"10.1109\/CVPR52729.2023.00434"},{"key":"e_1_2_10_40_1","unstructured":"M. PTran. \u201c3D Contour Closing: A Local Operator Based on Chamfer Distance Transformation \u201d accessed on May 1 2023 https:\/\/hal.science\/hal\u201000802068."},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_2_10_42_1","unstructured":"I.Gulrajani F.Ahmed M.Arjovsky V.Dumoulin andA. C.Courville \u201cImproved Training of Wasserstein GANs \u201d inAdvances in Neural Information Processing Systems(Curran Associates Inc. 2017)."},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"e_1_2_10_44_1","unstructured":"A. X.Chang T.Funkhouser L.Guibas et\u00a0al. \u201cShapeNet: An Information\u2010Rich 3D Model Repository \u201d arXiv:1512.03012 (2015)."},{"key":"e_1_2_10_45_1","doi-asserted-by":"crossref","unstructured":"D.Shu S. W.Park andJ.Kwon \u201c3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions \u201d in2019 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2019) 3858\u20133867.","DOI":"10.1109\/ICCV.2019.00396"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_22"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3193449"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339130"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70104","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70104","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:04:46Z","timestamp":1778285086000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70104"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70104","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-11-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70104"}}