{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:59Z","timestamp":1779948119441,"version":"3.53.1"},"reference-count":114,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00145","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1522-1533","source":"Crossref","is-referenced-by-count":0,"title":["PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers"],"prefix":"10.1109","author":[{"given":"Songlin","family":"Li","sequence":"first","affiliation":[{"name":"Stanford University,Stanford,CA,USA,94305"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Despoina","family":"Paschalidou","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA,94305"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA,94305"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achlioptas","year":"2018","journal-title":"Learning representations and generative models for 3d point clouds"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00518"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00264"},{"key":"ref4","article-title":"The tools of generative art, from flash to neural networks","author":"Bailey","year":"2020","journal-title":"Art in America"},{"key":"ref5","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"NeurIPS"},{"key":"ref6","author":"Brock","year":"2016","journal-title":"Generative and discriminative voxel modeling with convolutional neural networks"},{"key":"ref7","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_22"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref11","author":"Chen","year":"2020","journal-title":"Generative pretraining from pixels"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00011"},{"key":"ref17","article-title":"Learning elementary structures for 3d shape generation and matching","author":"Deprelle","year":"2019","journal-title":"NeurIPS"},{"key":"ref18","author":"Dhariwal","year":"2020","journal-title":"Jukebox: A generative model for music"},{"key":"ref19","article-title":"NICE: non-linear independent components estimation","author":"Dinh","year":"2015","journal-title":"ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00823"},{"key":"ref21","article-title":"Learning to infer graphics programs from hand-drawn images","author":"Ellis","year":"2018","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00053"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00048"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"ref29","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref30","author":"Gropp","year":"2020","journal-title":"Implicit geometric regularization for learning shapes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00030"},{"key":"ref32","article-title":"Stylenerf: A style-based 3d aware generator for highresolution image synthesis","author":"Gu","year":"2022","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00765"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530084"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2018.00141"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00270"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_49"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_23"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref44","author":"Katharopoulos","year":"2020","journal-title":"Transformers are rnns: Fast autoregressive transformers with linear attention"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073637"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1145\/3450626.3459766","article-title":"SPGAN: sphere-guided 3d shape generation and manipulation","author":"Li","year":"2021","journal-title":"ACM Trans. on Graphics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00308"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00591"},{"key":"ref50","article-title":"Editgan: Highprecision semantic image editing","author":"Ling","year":"2021","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00008"},{"key":"ref52","article-title":"Learning to describe scenes with programs","author":"Liu","year":"2019","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01593"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00484"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2049"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356527"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00888"},{"key":"ref63","author":"Nash","year":"2020","journal-title":"Polygen: An autoregressive generative model of 3d meshes"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00255"},{"key":"ref65","author":"Nguyen-Phuoc","year":"2020","journal-title":"Blockgan: Learning 3d object-aware scene representations from unlabelled images"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00356"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00475"},{"key":"ref68","article-title":"Scaling neural machine translation. In Proceedings of the Third Conference on Machine Translation: Research Papers","volume-title":"WMT 2018","author":"Ott","year":"2018"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01006"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00025"},{"key":"ref71","author":"Parmar","year":"2018","journal-title":"Image transformer"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01059"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00114"},{"key":"ref74","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","author":"Paschalidou","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00322"},{"key":"ref76","author":"Pavllo","year":"2020","journal-title":"Convolutional generation of textured 3d meshes"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01362"},{"key":"ref78","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref79","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref80","article-title":"Unsupervised learning of 3d structure from images","author":"Jimenez Rezende","year":"2016","journal-title":"NeurIPS"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref84","article-title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications","author":"Salimans","year":"2017","journal-title":"ICLR"},{"key":"ref85","author":"Schwarz","year":"2020","journal-title":"Graf: Generative radiance fields for 3d-aware image synthesis"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00578"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-2074"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00209"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref92","article-title":"Learning to infer and execute 3d shape programs","author":"Tian","year":"2019","journal-title":"ICLR"},{"key":"ref93","author":"Tulsiani","year":"2021","journal-title":"Pixeltransformer: Sample conditioned signal generation"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.160"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref97","article-title":"A geometric analysis of deep generative image models and its applications","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/3dv53792.2021.00021"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2011.01885.x"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00091"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00278"},{"key":"ref104","article-title":"DISN: deep implicit surface network for high-quality single-view 3d reconstruction","author":"Xu","year":"2019","journal-title":"NeurIPS"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00464"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01274"},{"key":"ref107","author":"Yao","year":"2022","journal-title":"LASSIE: learning articulated shapes from sparse image ensemble via 3d part discovery"},{"key":"ref108","article-title":"Multiview neural surface reconstruction by disentangling geometry and appearance","author":"Yariv","year":"2020","journal-title":"NeurIPS"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"ref110","article-title":"Image gans meet differentiable rendering for inverse graphics and interpretable 3d neural rendering","author":"Zhang","year":"2021","journal-title":"ICLR"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.103"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533339.pdf?arnumber=11533339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:03:12Z","timestamp":1779944592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":114,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00145","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}