{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:29Z","timestamp":1777865309978,"version":"3.51.4"},"reference-count":85,"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\/iccv51701.2025.00870","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9320-9331","source":"Crossref","is-referenced-by-count":0,"title":["Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians"],"prefix":"10.1109","author":[{"given":"Quankai","family":"Gao","sequence":"first","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iliyan","family":"Georgiev","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuanfeng Y.","family":"Wang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Krishna Kumar","family":"Singh","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulrich","family":"Neumann","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae Shin","family":"Yoon","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1887\/0750303123\/b365c48"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1348\/000711010X522227"},{"key":"ref3","author":"Brock","year":"2016","journal-title":"Generative and discriminative voxel modeling with convolutional neural networks. arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1568"},{"key":"ref5","article-title":"Shapenet: An information-rich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Meshanything: Artist-created mesh generation with autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Gaussianpro: 3d gaussian splatting with progressive propagation","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Cheng","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref9","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Spconv Contributors","volume-title":"Spconv: Spatially sparse convolution library","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Scenescape: Text-driven consistent scene generation","author":"Fridman","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref19","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref21","article-title":"Perceiver io: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle","year":"2021"},{"key":"ref23","article-title":"Leap: Liberate sparse-view 3d modeling from camera poses","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Shap-e: Generating conditional 3d implicit functions","author":"Jun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3658160"},{"key":"ref27","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref30","article-title":"Instant3d: Fast text-to-3d with sparse-view generation and large reconstruction model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_30"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_17"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00494"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref39","article-title":"Learning disentangled representations of timbre and pitch for musical instrument sounds using gaussian mixture variational autoencoders","author":"Luo","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292218"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref45","article-title":"Point-e: A system for generating 3d point clouds from complex prompts","author":"Nichol","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","author":"Poole","year":"2022","journal-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint"},{"key":"ref49","author":"Qi","year":"2016","journal-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation. arXiv preprint"},{"key":"ref50","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi","year":"2017"},{"key":"ref51","author":"Qi","year":"2017","journal-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv preprint"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687699"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref58","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"A tutorial on principal component analysis","author":"Shlens","year":"2014","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01855"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00067"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00972"},{"key":"ref63","author":"Szymanowicz","year":"2025","journal-title":"Bolt3d: Generating 3d scenes in seconds. arXiv preprint"},{"key":"ref64","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume":"33","author":"Tancik","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref65","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref68","article-title":"NVAE: A deep hierarchical variational autoencoder","author":"Vahdat","year":"2020","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"issue":"11","key":"ref69","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref70","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00514"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.255"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"ref75","article-title":"Dmv3d: Denoising multi-view diffusion using 3d large reconstruction model","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors","author":"Yi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00555"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref81","article-title":"Gaussiancube: Structuring gaussian splatting using optimal transport for 3d generative modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref84","article-title":"Cv-vae: A compatible video vae for latent generative video models","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"}],"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\/11445470.pdf?arnumber=11445470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:50Z","timestamp":1777529690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445470\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00870","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}