{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T04:57:36Z","timestamp":1774846656979,"version":"3.50.1"},"reference-count":173,"publisher":"Tsinghua University Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.26599\/cvm.2025.9450452","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:36:22Z","timestamp":1740422182000},"page":"1-28","source":"Crossref","is-referenced-by-count":9,"title":["Diffusion Models for 3D Generation: A Survey"],"prefix":"10.26599","volume":"11","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[{"name":"University of Pennsylvania,Department of Computer and Information Science,Philadelphia,Pennsylvania,USA,19104"}]},{"given":"Hao-Yang","family":"Peng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"}]},{"given":"Ying-Tian","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"}]},{"given":"Jiatao","family":"Gu","sequence":"additional","affiliation":[{"name":"Machine Learning Research, Apple AI\/ML,New York,USA"}]},{"given":"Shi-Min","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"}]}],"member":"11138","reference":[{"key":"ref1","volume-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref3","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"2","author":"Rezende","year":"2015"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref6","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Saharia","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/9781118818565.ch2"},{"key":"ref9","volume-title":"Text-to-image diffusion models in generative AI: A survey","author":"Zhang","year":"2023"},{"key":"ref10","volume-title":"Generative AI meets 3D: A survey on text-to-3D in AIGC era","author":"Li","year":"2023"},{"key":"ref11","volume-title":"Deep generative models on 3D representations: A survey","author":"Shi","year":"2022"},{"key":"ref12","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref13","volume-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"ref15","volume-title":"Factor fields: A unified framework for neural fields and beyond","author":"Chen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref20","article-title":"DreamFusion: Text-to-3D using 2D diffusion","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Poole","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"ref23","first-page":"8406","article-title":"ProlificDreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Wang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref25","article-title":"DreamGaussian: Generative Gaussian splatting for efficient 3D content creation","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Tang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"ref30","volume-title":"DITTO-NeRF: Diffusionbased iterative text to omni-directional 3D model","author":"Seo","year":"2023"},{"key":"ref31","volume-title":"Let 2D diffusion model know 3D-consistency for robust text-to-3D generation","author":"Seo","year":"2023"},{"key":"ref32","volume-title":"Textdriven visual synthesis with latent diffusion prior","author":"Liao","year":"2023"},{"key":"ref33","volume-title":"Re-imagine the negative prompt algorithm: Transform 2D diffusion into 3D, alleviate Janus problem and Beyond","author":"Armandpour","year":"2023"},{"key":"ref34","volume-title":"HiFA: High-fidelity text-to-3D with advanced diffusion guidance","author":"Zhu","year":"2023"},{"key":"ref35","volume-title":"DreamTime: An improved optimization strategy for text-to-3D content creation","author":"Huang","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01645"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_18"},{"key":"ref38","first-page":"39897","article-title":"SceneScape: Text-driven consistent scene generation","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Fridman","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref41","first-page":"21878","article-title":"PANOGEN: text-conditioned panoramic environment generation for vision-and-language navigation","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Li","year":"2023"},{"key":"ref42","volume-title":"MVDiffusion: Enabling holistic multi-view image generation with correspondence-aware diffusion","author":"Tang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00314"},{"key":"ref45","volume-title":"CompoNeRF: Text-guided multi-object compositional NeRF with editable 3D scene layout","author":"Lin","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01977"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00816"},{"key":"ref49","volume-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref51","first-page":"3307","article-title":"DreamSparse: Escaping from plato\u2019s cave with 2D diffusion model given sparse views","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Yoo","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref54","article-title":"Magic123: One image to high-quality 3D object generation using both 2D and 3D diffusion priors","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Qian","year":"2023"},{"key":"ref55","first-page":"22226","article-title":"One-2-3-45: Any single image to 3D mesh in 45 seconds without per-shape optimization","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Liu","year":"2023"},{"key":"ref56","article-title":"Mvdream: Multiview diffusion for 3D generation","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Shi","year":"2023"},{"key":"ref57","volume-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023"},{"key":"ref58","volume-title":"Zero123++: A single image to consistent multi-view diffusion base model","author":"Shi","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"ref60","article-title":"Instant3D: Fast text-to-3D with sparse-view generation and large reconstruction model","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Li","year":"2023"},{"key":"ref61","volume-title":"ImageDream: Image-prompt multi-view diffusion for 3D generation","author":"Wang","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref64","volume-title":"InstantMesh: Efficient 3D mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024"},{"key":"ref65","volume-title":"GECO: Generative image-to-3D within a SECOnd","author":"Wang","year":"2024"},{"key":"ref66","volume-title":"CAT3D: Create anything in 3D with multi-view diffusion models","author":"Gao","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3592094"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00347"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01322"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00097"},{"key":"ref71","first-page":"4566","article-title":"DreamWaltz: Make a scene with complex 3D animatable avatars","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Huang","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00150"},{"key":"ref73","first-page":"10516","article-title":"DreamHuman: Animatable 3D avatars from text","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Kolotouros","year":"2023"},{"key":"ref74","volume-title":"ZeroAvatar: Zero-shot 3D avatar generation from a single image","author":"Weng","year":"2023"},{"key":"ref75","volume-title":"AvatarBooth: High-quality and customizable 3D human avatar generation","author":"Zeng","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00051"},{"key":"ref77","first-page":"48173","article-title":"ARTIC3D: Learning robust articulated 3D shapes from noisy web image collections","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Yao","year":"2023"},{"key":"ref78","first-page":"19683","article-title":"Instruct-NeRF2-NeRF: Editing 3D scenes with instructions","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Haque","year":"2023"},{"key":"ref79","volume-title":"Instruct 3D-to-3D: Text instruction guided 3D-to-3D conversion","author":"Kamata","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref81","volume-title":"Edit-DiffNeRF: Editing 3D neural radiance fields using 2D diffusion model","author":"Yu","year":"2023"},{"key":"ref82","volume-title":"Control4D: Efficient 4D portrait editing with text","author":"Shao","year":"2023"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/201"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618190"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28113"},{"key":"ref86","volume-title":"threestudio: A unified framework for 3D content generation","author":"Guo","year":"2023"},{"key":"ref87","volume-title":"Novel view synthesis with diffusion models","author":"Watson","year":"2022"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"ref89","volume-title":"NerfDiff: Single-image view synthesis with NeRF-guided distillation from 3D-aware diffusion","author":"Gu","year":"2023"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref91","volume-title":"3DDesigner: Towards photorealistic 3D object generation and editing with text-guided diffusion models","author":"Li","year":"2022"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01211"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01213"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref95","first-page":"12349","article-title":"Diffusion with forward models: Solving stochastic inverse problems without direct supervision","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Tewari","year":"2023"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00814"},{"key":"ref97","article-title":"DMV3D: Denoising multi-view diffusion using 3D large reconstruction model","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Xu","year":"2023"},{"key":"ref98","article-title":"LRM: Large reconstruction model for single image to 3D","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Hong","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00226"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00204"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00443"},{"key":"ref106","volume-title":"3DGen: Triplane latent diffusion for textured mesh generation","author":"Gupta","year":"2023"},{"key":"ref107","first-page":"6087","article-title":"Deep marching tetrahedra: A hybrid representation for high-resolution 3D shape synthesis","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Shen","year":"2021"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00229"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00030"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00215"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"ref114","volume-title":"3D-LDM: Neural implicit 3D shape generation with latent diffusion models","author":"Nam","year":"2022"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365171.2337"},{"key":"ref117","first-page":"965","article-title":"Point-voxel CNN for efficient 3D deep learning","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Liu","year":"2019"},{"issue":"4","key":"ref118","doi-asserted-by":"crossref","DOI":"10.1145\/3592442","article-title":"3D Shape2VecSet: A 3D shape representation for neural fields and generative diffusion models","volume":"42","author":"Zhang","year":"2023","journal-title":"ACM Transactions on Graphics"},{"key":"ref119","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Karras","year":"2022"},{"key":"ref120","volume-title":"Shap-E: Generating conditional 3D implicit functions","author":"Jun","year":"2023"},{"key":"ref121","first-page":"25102","article-title":"GAUDI: A neural architect for immersive 3D scene generation","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Bautista","year":"2022"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref124","volume-title":"StyleAvatar3D: Leveraging image-text diffusion models for high-fidelity 3D avatar generation","author":"Zhang","year":"2023"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"ref127","volume-title":"MeshDiffusion: Score-based generative 3D mesh modeling","author":"Liu","year":"2023"},{"key":"ref128","volume-title":"Point-E: A system for generating 3D point clouds from complex prompts","author":"Nichol","year":"2022"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00034"},{"key":"ref130","volume-title":"Learning a diffusion prior for NeRFs","author":"Yang","year":"2023"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_21"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555394"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3635304"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3592103"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01315"},{"key":"ref136","first-page":"75951","article-title":"Diffcomplete: Diffusion-based generative 3D shape completion","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Chu","year":"2024"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00433"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26293-7_4"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00577"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00820"},{"key":"ref143","volume-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","author":"Qi","year":"2017"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02100"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01311"},{"key":"ref147","volume-title":"GVGEN: Text-to-3D generation with volumetric representation","author":"He","year":"2024"},{"key":"ref148","volume-title":"GaussianCube: A structured and explicit radiance representation for 3D generative modeling","author":"Zhang","year":"2024"},{"key":"ref149","volume-title":"ShapeNet: An information-rich 3D model repository","author":"Chang","year":"2015"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560844"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01023"},{"key":"ref153","volume-title":"A large dataset of object scans","author":"Choi","year":"2016"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275066"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_7"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00903"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00314"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01388"},{"key":"ref166","volume-title":"ARKitScenes: A diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data","author":"Baruch","year":"2021"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref168","volume-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref169","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Dosovitskiy","year":"2017"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01263"},{"key":"ref173","volume-title":"T3Bench: Benchmarking current progress in text-to-3D generation","author":"He","year":"2023"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10903665\/10901942.pdf?arnumber=10901942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:34:36Z","timestamp":1741714476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10901942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":173,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450452","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}