{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:33:42Z","timestamp":1726763622607},"reference-count":65,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"Foundation for Food and Agriculture Research, United States","award":["602757"]},{"name":"PERSEUS","award":["2023-68012-38992"]},{"DOI":"10.13039\/100005825","name":"USDA NIFA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2024,2,29]]},"abstract":"We show how a Transformer can encode hierarchical tree-like string structures by introducing a new deep learning-based framework for generating 3D biological tree models represented as Lindenmayer system (L-system) strings. L-systems are string-rewriting procedural systems that encode tree topology and geometry. L-systems are efficient, but creating the production rules is one of the most critical problems precluding their usage in practice. We substitute the procedural rules creation with a deep neural model. Instead of writing the rules, we train a deep neural model that produces the output strings. We train our model on 155k tree geometries that are encoded as L-strings, de-parameterized, and converted to a hierarchy of linear sequences corresponding to branches. An end-to-end deep learning model with an attention mechanism then learns the distributions of geometric operations and branches from the input, effectively replacing the L-system rewriting rule generation. The trained deep model generates new L-strings representing 3D tree models in the same way L-systems do by providing the starting string. Our model allows for the generation of a wide variety of new trees, and the deep model agrees with the input by 93.7% in branching angles, 97.2% in branch lengths, and 92.3% in an extracted list of geometric features. We also validate the generated trees using perceptual metrics showing 97% agreement with input geometric models.<\/jats:p>","DOI":"10.1145\/3627101","type":"journal-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T11:27:18Z","timestamp":1696937238000},"page":"1-16","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Latent L-systems: Transformer-based Tree Generator"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-0445-3141","authenticated-orcid":false,"given":"Jae Joong","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Computer Science, Purdue University, USA"}]},{"ORCID":"http:\/\/orcid.org\/0009-0006-6490-1184","authenticated-orcid":false,"given":"Bosheng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Purdue University, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5293-2112","authenticated-orcid":false,"given":"Bedrich","family":"Benes","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Purdue University, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,11,2]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.1984.276141"},{"key":"e_1_3_4_3_1","first-page":"27","volume-title":"Proceedings of the Ausgraph","author":"Arvo J.","year":"1988","unstructured":"J. Arvo and D. Kirk. 1988. Modeling plants with environment-sensitive automata. In Proceedings of the Ausgraph. 27\u201333."},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100893"},{"key":"e_1_3_4_5_1","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher M.","year":"2006","unstructured":"Christopher M. Bishop and Nasser M. Nasrabadi. 2006. Pattern Recognition and Machine Learning. Vol. 4. Springer."},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778841"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00275"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/378456.378505"},{"key":"e_1_3_4_10_1","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805. Retrieved from https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"e_1_3_4_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs11182074"},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275006"},{"key":"e_1_3_4_14_1","unstructured":"William Fedus Ian Goodfellow and Andrew M. Dai. 2018. Maskgan: Better text generation via filling in the_. arXiv:1801.07736. Retrieved from https:\/\/arxiv.org\/abs\/1801.07736"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90418-4_2"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356488"},{"key":"e_1_3_4_17_1","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in Neural Information Processing Systems 27 (2014), 2672\u20132680.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_4_18_1","article-title":"Grundrib der gasamten Gew\u00e4sserkunde,band I: Flubkunde","volume":"1","author":"Gravelius H.","year":"1914","unstructured":"H. Gravelius. 1914. Grundrib der gasamten Gew\u00e4sserkunde,band I: Flubkunde. kompendium of Hydrology 1 (1914), 265\u2013278.","journal-title":"kompendium of Hydrology"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/74334.74351"},{"key":"e_1_3_4_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394105"},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11957"},{"key":"e_1_3_4_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01391.x"},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459954"},{"key":"e_1_3_4_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13106"},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8659.1310057"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417812"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_4_29_1","first-page":"403","volume-title":"Proceedings of the 4th International Workshop on Functional-structural Plant Models","author":"Karwowski Radoslaw","year":"2004","unstructured":"Radoslaw Karwowski and Przemyslaw Prusinkiewicz. 2004. The l-system-based plant-modeling environment l-studio 4.0. In Proceedings of the 4th International Workshop on Functional-structural Plant Models. UMR AMAP Montpellier, France, 403\u2013405."},{"key":"e_1_3_4_30_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_4_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480525"},{"key":"e_1_3_4_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592145"},{"issue":"4","key":"e_1_3_4_33_1","first-page":"1","article-title":"Grass: Generative recursive autoencoders for shape structures","volume":"36","author":"Li Jun","year":"2017","unstructured":"Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, and Leonidas Guibas. 2017. Grass: Generative recursive autoencoders for shape structures. ACM Transactions on Graphics 36, 4 (2017), 1\u201314.","journal-title":"ACM Transactions on Graphics"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.03.050"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-5193(68)90079-9"},{"key":"e_1_3_4_36_1","first-page":"107","volume-title":"Proceedings of the SBIM Expressive","author":"Longay Steven","year":"2012","unstructured":"Steven Longay, Adam Runions, Fr\u00e9d\u00e9ric Boudon, and Przemyslaw Prusinkiewicz. 2012. TreeSketch: Interactive procedural modeling of trees on a tablet. In Proceedings of the SBIM Expressive. 107\u2013120."},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-005-0289-z"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0093535"},{"key":"e_1_3_4_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356527"},{"key":"e_1_3_4_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237279"},{"key":"e_1_3_4_41_1","first-page":"7220","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Nash Charlie","year":"2020","unstructured":"Charlie Nash, Yaroslav Ganin, S.M. Ali Eslami, and Peter Battaglia. 2020. Polygen: An autoregressive generative model of 3d meshes. In Proceedings of the International Conference on Machine Learning. PMLR, 7220\u20137229."},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0056876"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281500.1281537"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/15886.15892"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531364"},{"key":"e_1_3_4_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897826.2927332"},{"key":"e_1_3_4_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661252"},{"key":"e_1_3_4_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185546"},{"key":"e_1_3_4_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480519"},{"key":"e_1_3_4_50_1","doi-asserted-by":"publisher","DOI":"10.5555\/16564.16608"},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/166117.166161"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/103356.103565"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.5555\/83596"},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12276"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/800031.808571"},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12282"},{"key":"e_1_3_4_57_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2 (NIPS\u201914) . MIT Press Cambridge MA 3104\u20133112."},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366187"},{"key":"e_1_3_4_59_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS\u201917) . Curran Associates Inc. Red Hook NY 6000\u20136010."},{"key":"e_1_3_4_60_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13501"},{"key":"e_1_3_4_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218427"},{"key":"e_1_3_4_62_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"e_1_3_4_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601162"},{"key":"e_1_3_4_64_1","first-page":"28877","volume-title":"Proceedings of the Advances in Neural Information Processing Systems.","volume":"34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation?. In Proceedings of the Advances in Neural Information Processing Systems.M. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34, Curran Associates, Inc., 28877\u201328888. Retrieved from https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/f1c1592588411002af340cbaedd6fc33-Paper.pdf"},{"key":"e_1_3_4_65_1","unstructured":"Seongjun Yun Minbyul Jeong Raehyun Kim Jaewoo Kang and Hyunwoo J. Kim. 2019. Graph transformer networks. Proceedings of the 33rd International Conference on Neural Information Processing Systems . Curran Associates Inc. Red Hook NY Article 1073 11983\u201311993."},{"key":"e_1_3_4_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3307887"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T12:21:35Z","timestamp":1698927695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,2]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2,29]]}},"alternative-id":["10.1145\/3627101"],"URL":"https:\/\/doi.org\/10.1145\/3627101","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,2]]},"assertion":[{"value":"2022-10-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-29","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
