{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:40Z","timestamp":1784268640628,"version":"3.55.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2017,7,20]],"date-time":"2017-07-20T00:00:00Z","timestamp":1500508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61572507, 61532003, 61622212"],"award-info":[{"award-number":["61572507, 61532003, 61622212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100005144","name":"Qualcomm","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100005144","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-1528025, DMS-1546206"],"award-info":[{"award-number":["IIS-1528025, DMS-1546206"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Adobe"},{"name":"Vicarious"},{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"crossref","award":["611370"],"award-info":[{"award-number":["611370"]}],"id":[{"id":"10.13039\/501100000038","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":[[2017,8,31]]},"abstract":"<jats:p>\n            We introduce a novel neural network architecture for\n            <jats:italic>encoding<\/jats:italic>\n            and\n            <jats:italic>synthesis<\/jats:italic>\n            of 3D shapes, particularly their\n            <jats:italic>structures.<\/jats:italic>\n            Our key insight is that 3D shapes are effectively characterized by their\n            <jats:italic>hierarchical<\/jats:italic>\n            organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a\n            <jats:italic>recursive<\/jats:italic>\n            neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry.\n          <\/jats:p>","DOI":"10.1145\/3072959.3073637","type":"journal-article","created":{"date-parts":[[2017,7,21]],"date-time":"2017-07-21T12:24:07Z","timestamp":1500639847000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":232,"title":["GRASS"],"prefix":"10.1145","volume":"36","author":[{"given":"Jun","family":"Li","sequence":"first","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology and Shenzhen University, and Shandong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddhartha","family":"Chaudhuri","sequence":"additional","affiliation":[{"name":"IIT Bombay"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ersin","family":"Yumer","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,7,20]]},"reference":[{"key":"e_1_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601102"},{"key":"e_1_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1201775.882311"},{"key":"e_1_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073207"},{"key":"e_1_2_2_4_1","volume-title":"arXiv preprint arXiv:1701.07875","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky , Soumith Chintala , and L\u00e9on Bottou . 2017. Wasserstein GAN. arXiv preprint arXiv:1701.07875 ( 2017 ). Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein GAN. arXiv preprint arXiv:1701.07875 (2017)."},{"key":"e_1_2_2_5_1","volume":"201","author":"Averkiou Melinos","unstructured":"Melinos Averkiou , Vladimir Kim , Youyi Zheng , and Niloy J. Mitra. 201 4. ShapeSynth: Parameterizing Model Collections for Coupled Shape Exploration and Synthesis. EUROGRAPHICS (2014). Melinos Averkiou, Vladimir Kim, Youyi Zheng, and Niloy J. Mitra. 2014. ShapeSynth: Parameterizing Model Collections for Coupled Shape Exploration and Synthesis. EUROGRAPHICS (2014).","journal-title":"Niloy J. Mitra."},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1833349.1778841"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964930"},{"key":"e_1_2_2_9_1","volume-title":"Adams","author":"Duvenaud David","year":"2015","unstructured":"David Duvenaud , Dougal Maclaurin , Jorge Aguilera-Iparraguirre , Rafael G\u00f3mez-Bombarelli , Timothy Hirzel , Al'an Aspuru-Guzik , and Ryan P . Adams . 2015 . Convolutional Networks on Graphs for Learning Molecular Fingerprints. In Proc. NIPS. David Duvenaud, Dougal Maclaurin, Jorge Aguilera-Iparraguirre, Rafael G\u00f3mez-Bombarelli, Timothy Hirzel, Al'an Aspuru-Guzik, and Ryan P. Adams. 2015. Convolutional Networks on Graphs for Learning Molecular Fingerprints. In Proc. NIPS."},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601185"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_29"},{"key":"e_1_2_2_12_1","volume-title":"Proc. NIPS.","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 . In Proc. NIPS. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proc. NIPS."},{"key":"e_1_2_2_13_1","volume-title":"Deep Convolutional Networks on Graph-Structured Data. CoRR abs\/1506.05163","author":"Henaff Mikael","year":"2015","unstructured":"Mikael Henaff , Joan Bruna , and Yann LeCun . 2015. Deep Convolutional Networks on Graph-Structured Data. CoRR abs\/1506.05163 ( 2015 ). http:\/\/arxiv.org\/abs\/1506.05163 Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep Convolutional Networks on Graph-Structured Data. CoRR abs\/1506.05163 (2015). http:\/\/arxiv.org\/abs\/1506.05163"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12694"},{"key":"e_1_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Arjun Jain Thorsten Thorm\u00e4hlen Tobias Ritschel and Hans-Peter Seidel. 2012. Exploring Shape Variations by 3D-Model Decomposition and Part-based Recombination. In EUROGRAPHICS.  Arjun Jain Thorsten Thorm\u00e4hlen Tobias Ritschel and Hans-Peter Seidel. 2012. Exploring Shape Variations by 3D-Model Decomposition and Part-based Recombination. In EUROGRAPHICS.","DOI":"10.1111\/j.1467-8659.2012.03042.x"},{"key":"e_1_2_2_16_1","volume-title":"A probabilistic model for component-based shape synthesis. ACM Trans. Graph. (Proc. SIGGRAPH) 31, 4","author":"Kalogerakis Evangelos","year":"2012","unstructured":"Evangelos Kalogerakis , Siddhartha Chaudhuri , Daphne Koller , and Vladlen Koltun . 2012. A probabilistic model for component-based shape synthesis. ACM Trans. Graph. (Proc. SIGGRAPH) 31, 4 ( 2012 ). Evangelos Kalogerakis, Siddhartha Chaudhuri, Daphne Koller, and Vladlen Koltun. 2012. A probabilistic model for component-based shape synthesis. ACM Trans. Graph. (Proc. SIGGRAPH) 31, 4 (2012)."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461933"},{"key":"e_1_2_2_18_1","unstructured":"W. K\u00f6hler. 1929. Gestalt Psychology. Liveright.  W. K\u00f6hler. 1929. Gestalt Psychology. Liveright."},{"key":"e_1_2_2_19_1","volume-title":"S\u00f8ren Kaae S\u00f8nderby, and Ole Winther","author":"Lindbo Larsen Anders Boesen","year":"2015","unstructured":"Anders Boesen Lindbo Larsen , S\u00f8ren Kaae S\u00f8nderby, and Ole Winther . 2015 . Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015). Anders Boesen Lindbo Larsen, S\u00f8ren Kaae S\u00f8nderby, and Ole Winther. 2015. Autoencoding beyond pixels using a learned similarity metric. arXiv preprint arXiv:1512.09300 (2015)."},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2542266.2542267"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141931"},{"key":"e_1_2_2_23_1","volume-title":"Proc. ICML.","author":"Niepert Mathias","year":"2016","unstructured":"Mathias Niepert , Mohamed Ahmed , and Konstantin Kutzkov . 2016 . Learning Convolutional Neural Networks for Graphs . In Proc. ICML. Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. 2016. Learning Convolutional Neural Networks for Graphs. In Proc. ICML."},{"key":"e_1_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964928"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.609"},{"key":"e_1_2_2_26_1","volume-title":"Pitchaya Sitthi-Amorn, and Wojciech Matusik.","author":"Schulz Adriana","year":"2016","unstructured":"Adriana Schulz , Ariel Shamir , Ilya Baran , David Isaac William Levin , Pitchaya Sitthi-Amorn, and Wojciech Matusik. 2016 . Retrieval on Parametric Shape Collections. ACM Trans. Graph . (to appear) (2016). Adriana Schulz, Ariel Shamir, Ilya Baran, David Isaac William Levin, Pitchaya Sitthi-Amorn, and Wojciech Matusik. 2016. Retrieval on Parametric Shape Collections. ACM Trans. Graph. (to appear) (2016)."},{"key":"e_1_2_2_27_1","volume-title":"Encyclopedia of Computational Neuroscience","author":"Serre Thomas","unstructured":"Thomas Serre . 2013. Hierarchical Models of the Visual System . In Encyclopedia of Computational Neuroscience , Dieter Jaeger and Ranu Jung (Eds.). Springer NY. Thomas Serre. 2013. Hierarchical Models of the Visual System. In Encyclopedia of Computational Neuroscience, Dieter Jaeger and Ranu Jung (Eds.). Springer NY."},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_14"},{"key":"e_1_2_2_30_1","volume-title":"Ng","author":"Socher Richard","year":"2012","unstructured":"Richard Socher , Brody Huval , Bharath Bhat , Christopher D. Manning , and Andrew Y . Ng . 2012 . Convolutional-Recursive Deep Learning for 3D Object Classification. In Proc. NIPS. Richard Socher, Brody Huval, Bharath Bhat, Christopher D. Manning, and Andrew Y. Ng. 2012. Convolutional-Recursive Deep Learning for 3D Object Classification. In Proc. NIPS."},{"key":"e_1_2_2_31_1","volume-title":"Manning","author":"Socher Richard","year":"2011","unstructured":"Richard Socher , Cliff C. Lin , Andrew Y. Ng , and Christopher D . Manning . 2011 . Parsing Natural Scenes and Natural Language with Recursive Neural Networks. In Proc. ICML. Richard Socher, Cliff C. Lin, Andrew Y. Ng, and Christopher D. Manning. 2011. Parsing Natural Scenes and Natural Language with Recursive Neural Networks. In Proc. ICML."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2380116.2380127"},{"key":"e_1_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/1661412.1618513"},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.160"},{"key":"e_1_2_2_36_1","volume-title":"WaveNet: A Generative Model for Raw Audio. CoRR abs\/1609.03499","author":"van den Oord A\u00e4ron","year":"2016","unstructured":"A\u00e4ron van den Oord , Sander Dieleman , Heiga Zen , Karen Simonyan , Oriol Vinyals , Alex Graves , Nal Kalchbrenner , Andrew W. Senior , and Koray Kavukcuoglu . 2016a. WaveNet: A Generative Model for Raw Audio. CoRR abs\/1609.03499 ( 2016 ). http:\/\/arxiv.org\/abs\/1609.03499 A\u00e4ron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew W. Senior, and Koray Kavukcuoglu. 2016a. WaveNet: A Generative Model for Raw Audio. CoRR abs\/1609.03499 (2016). http:\/\/arxiv.org\/abs\/1609.03499"},{"key":"e_1_2_2_37_1","volume-title":"Pixel Recurrent Neural Networks. CoRR abs\/1601.06759","author":"van den Oord A\u00e4ron","year":"2016","unstructured":"A\u00e4ron van den Oord , Nal Kalchbrenner , and Koray Kavukcuoglu . 2016b. Pixel Recurrent Neural Networks. CoRR abs\/1601.06759 ( 2016 ). http:\/\/arxiv.org\/abs\/1601.06759 A\u00e4ron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu. 2016b. Pixel Recurrent Neural Networks. CoRR abs\/1601.06759 (2016). http:\/\/arxiv.org\/abs\/1601.06759"},{"key":"e_1_2_2_38_1","volume-title":"Conditional Image Generation with PixelCNN Decoders. CoRR abs\/1606.05328","author":"van den Oord A\u00e4ron","year":"2016","unstructured":"A\u00e4ron van den Oord , Nal Kalchbrenner , Oriol Vinyals , Lasse Espeholt , Alex Graves , and Koray Kavukcuoglu . 2016c. Conditional Image Generation with PixelCNN Decoders. CoRR abs\/1606.05328 ( 2016 ). http:\/\/arxiv.org\/abs\/1606.05328 A\u00e4ron van den Oord, Nal Kalchbrenner, Oriol Vinyals, Lasse Espeholt, Alex Graves, and Koray Kavukcuoglu. 2016c. Conditional Image Generation with PixelCNN Decoders. CoRR abs\/1606.05328 (2016). http:\/\/arxiv.org\/abs\/1606.05328"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461924"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01885.x"},{"key":"e_1_2_2_41_1","volume-title":"Tenenbaum","author":"Wu Jiajun","year":"2016","unstructured":"Jiajun Wu , Chengkai Zhang , Tianfan Xue , William T. Freeman , and Joshua B . Tenenbaum . 2016 . Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. In Proc. NIPS. Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, and Joshua B. Tenenbaum. 2016. Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. In Proc. NIPS."},{"key":"e_1_2_2_42_1","volume-title":"Proc. CVPR.","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu , Shuran Song , Aditya Khosla , Fisher Yu , Linguang Zhang , Xiaoou Tang , and Jianxiong Xiao . 2015 . 3D ShapeNets: A deep representation for volumetric shapes . In Proc. CVPR. Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proc. CVPR."},{"key":"e_1_2_2_43_1","volume-title":"Proc. NIPS.","author":"Yan Xinchen","year":"2016","unstructured":"Xinchen Yan , Jimei Yang , Ersin Yumer , Yijie Guo , and Honglak Lee . 2016 . Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision . In Proc. NIPS. Xinchen Yan, Jimei Yang, Ersin Yumer, Yijie Guo, and Honglak Lee. 2016. Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision. In Proc. NIPS."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_18"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073637","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073637","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3072959.3073637","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:37:23Z","timestamp":1750217843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073637"}},"subtitle":["generative recursive autoencoders for shape structures"],"short-title":[],"issued":{"date-parts":[[2017,7,20]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8,31]]}},"alternative-id":["10.1145\/3072959.3073637"],"URL":"https:\/\/doi.org\/10.1145\/3072959.3073637","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,20]]},"assertion":[{"value":"2017-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}