{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:10:38Z","timestamp":1778051438172,"version":"3.51.4"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00178","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1777-1787","source":"Crossref","is-referenced-by-count":0,"title":["BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity"],"prefix":"10.1109","author":[{"given":"Juil","family":"Koo","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Tung","family":"Lin","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanho","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanhyeok","family":"Park","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhyuk","family":"Sung","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Point-E: A system for generating 3d point clouds from complex prompts","author":"Alex","year":"2022"},{"key":"ref3","article-title":"Polydiff: Generating 3d polygonal meshes with diffusion models","author":"Alliegro","year":"2023"},{"key":"ref4","article-title":"Visual perception by computer","volume-title":"Proceedings of the IEEE Conference on Systems and Control (Miami, FL)","author":"Binford"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref7","article-title":"Shapenet: An informationrich 3d model repository","author":"Chang","year":"2015"},{"key":"ref8","article-title":"Pixart-{\\delta}: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00858"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00011"},{"key":"ref13","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023"},{"key":"ref15","author":"Gottschalk","year":"1996","journal-title":"OBB-Tree: a structure for rapid interference detection"},{"key":"ref16","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530084"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543434"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01802"},{"key":"ref20","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00128"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01311"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01328"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00736"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073637"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00276"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref32","article-title":"MeshDiffusion: Score-based generative 3d mesh modeling","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.1978.0020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356527"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref39","article-title":"3d-ldm: Neural implicit 3d shape generation with latent diffusion models","author":"Nam","year":"2022"},{"key":"ref40","article-title":"Polygen: An autoregressive generative model of 3d meshes","author":"Nash","year":"2020","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01148"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00146"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00114"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00322"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02107"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687699"},{"key":"ref50","author":"Sella","year":"2024","journal-title":"Spic-e: Structural priors in 3d diffusion models using cross-entity attention"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref53","article-title":"Pasta: Controllable part-aware shape generation with autoregressive transformers","author":"Songlin","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356529"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356529"},{"key":"ref56","article-title":"Edgerunner: Auto-regressive auto-encoder for artistic mesh generation","author":"Tang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.160"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref59","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref60","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.4324\/9781315785080"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70198"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3658129"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3526212"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459873"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818074"},{"key":"ref71","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","author":"Zibo","year":"2023","journal-title":"NeurIPS"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492050.pdf?arnumber=11492050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:11:17Z","timestamp":1778047877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00178","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}