{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:38Z","timestamp":1777888838209,"version":"3.51.4"},"reference-count":92,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01087","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11685-11696","source":"Crossref","is-referenced-by-count":1,"title":["Efficient Autoregressive Shape Generation Via Octree-Based Adaptive Tokenization"],"prefix":"10.1109","author":[{"given":"Kangle","family":"Deng","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsueh-Ti Derek","family":"Liu","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxia","family":"Sun","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Shang","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiran S.","family":"Bhat","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deva","family":"Ramanan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun-Yan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maneesh","family":"Agrawala","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tinghui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Roblox"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566652"},{"key":"ref3","article-title":"Demystifying mmd gans","volume-title":"International Conference on Learning Representations (ICLR)","author":"Bi\u0144kowski","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01515"},{"key":"ref7","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","author":"Chen","year":"2024","journal-title":"Meshanything v2: Artist-created mesh generation with adjacent mesh tokenization"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258849"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1061347.1061350"},{"key":"ref14","article-title":"Meshtron: High-fidelity, artist-like 3d mesh generation at scale","author":"Hao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref16","article-title":"Gans trained by a two timescale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","article-title":"Lrm: Large reconstruction model for single image to 3d","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hong","year":"2024"},{"key":"ref18","article-title":"Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks","volume-title":"International Conference on Machine Learning (ICML)","author":"Huh","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00270"},{"key":"ref20","article-title":"Perceiver: General perception with iterative attention","volume-title":"International Conference on Machine Learning (ICML)","author":"Jaegle","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566586"},{"key":"ref22","article-title":"Noise-free score distillation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Katzir","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref24","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref25","volume-title":"Flux","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref27","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","volume-title":"International Conference on Learning Representations (ICLR)","author":"Li","year":"2024"},{"key":"ref28","author":"Li","year":"2023","journal-title":"Sweetdreamer: Aligning geometric priors in 2d diffusion for consistent text-to-3d"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00500"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00037"},{"key":"ref31","article-title":"One-2\u20133-45: Any single image to 3d mesh in 45 seconds without per-shape optimization","author":"Liu","year":"2023","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"ref33","article-title":"Meshformer: High-quality mesh generation with 3d-guided reconstruction model","author":"Liu","year":"2025","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/280811.281026"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0818"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1064"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(82)90104-6"},{"key":"ref43","article-title":"Octree encoding: A new technique for the representation, manipulation and display of arbitrary 3-d objects by computer","author":"Meagher","year":"1980","journal-title":"Electrical and Systems Engineering Department Rensseiaer Polytechnic"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00069"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275066"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01112"},{"key":"ref52","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"International Conference on Learning Representations (ICLR)","author":"Poole","year":"2023"},{"issue":"8","key":"ref53","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref57","article-title":"Foundation AI Team Roblox. Cube: A roblox view of 3d intelligence","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"3","key":"ref59","article-title":"Octree-based pointcloud compression","volume":"3","author":"Schnabel","year":"2006","journal-title":"PBG@ SIGGRAPH"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref62","author":"Sun","year":"2023","journal-title":"Dreamcraft3d: Hierarchical 3d generation with bootstrapped diffusion prior"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1006\/ciun.1993.1029"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref65","article-title":"Edgerunner: Autoregressive auto-encoder for artistic mesh generation","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tang","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.230"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref69","article-title":"Triposr: Fast 3d object reconstruction from a single image","author":"Tochilkin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_13"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0728"},{"key":"ref72","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073608"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275050"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0368"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730601"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01036"},{"key":"ref79","article-title":"Direct3d: Scalable image-to-3d generation via 3d latent diffusion transformer","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3658188"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"ref82","article-title":"Octfusion: Octreebased diffusion models for 3d shape generation","author":"Xiong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Dmv3d: Denoising multi-view diffusion using 3d large reconstruction model","volume-title":"International Conference on Learning Representations (ICLR)","author":"Xu","year":"2024"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_15"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3592442"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3236"},{"key":"ref91","article-title":"Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00983"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443961.pdf?arnumber=11443961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:23Z","timestamp":1777611563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01087","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}