{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:37:38Z","timestamp":1775230658377,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":124,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747635","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:44:49Z","timestamp":1758959089000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1481-9290","authenticated-orcid":false,"given":"Jaewook","family":"Lee","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8911-3241","authenticated-orcid":false,"given":"Filippo","family":"Aleotti","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7481-802X","authenticated-orcid":false,"given":"Diego","family":"Mazala","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3215-7857","authenticated-orcid":false,"given":"Guillermo","family":"Garcia-Hernando","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3108-5030","authenticated-orcid":false,"given":"Sara","family":"Vicente","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3423-3526","authenticated-orcid":false,"given":"Oliver James","family":"Johnston","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2390-5892","authenticated-orcid":false,"given":"Isabel","family":"Kraus-Liang","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., San Francisco, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0891-0748","authenticated-orcid":false,"given":"Jakub","family":"Powierza","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9689-7841","authenticated-orcid":false,"given":"Donghoon","family":"Shin","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8291-3353","authenticated-orcid":false,"given":"Jon E.","family":"Froehlich","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-3828","authenticated-orcid":false,"given":"Gabriel","family":"Brostow","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom and Niantic Spatial, Inc., London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4831-6296","authenticated-orcid":false,"given":"Jessica","family":"Van Brummelen","sequence":"additional","affiliation":[{"name":"Niantic Spatial, Inc., London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Aarya and Flip Phillips. 2023. BlenderGPT. https:\/\/github.com\/gd3kr\/BlenderGPT."},{"key":"e_1_3_3_3_3_2","unstructured":"Adobe. 2024. Adobe Aero: Augmented reality. https:\/\/www.adobe.com\/uk\/products\/aero.html."},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661547"},{"key":"e_1_3_3_3_5_2","unstructured":"Andrea Agostinelli Timo\u00a0I. Denk Zal\u00e1n Borsos Jesse Engel Mauro Verzetti Antoine Caillon Qingqing Huang Aren Jansen Adam Roberts Marco Tagliasacchi Matt Sharifi Neil Zeghidour and Christian Frank. 2023. MusicLM: Generating Music From Text. arxiv:https:\/\/arXiv.org\/abs\/2301.11325\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2301.11325"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376722"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584060"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3660692"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Mark Billinghurst Adrian Clark Gun Lee et\u00a0al. 2015. A survey of augmented reality. Foundations and Trends\u00ae in Human\u2013Computer Interaction 8 2-3 (2015) 73\u2013272.","DOI":"10.1561\/1100000049"},{"key":"e_1_3_3_3_12_2","unstructured":"Blender. 2024. Blender 4.3. A stroke of genius. https:\/\/www.blender.org."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Mark Boss Zixuan Huang Aaryaman Vasishta and Varun Jampani. 2024. SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00653 (2024).","DOI":"10.1109\/CVPR52734.2025.01514"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3 2 (2006) 77\u2013101. 10.1191\/1478088706qp063oa arXiv:https:\/\/www.tandfonline.com\/doi\/pdf\/10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2019. Reflecting on reflexive thematic analysis. Qualitative Research in Sport Exercise and Health 11 4 (2019) 589\u2013597. 10.1080\/2159676X.2019.1628806 arXiv:10.1080\/2159676X.2019.1628806","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_3_3_16_2","unstructured":"J Brooke. 1996. SUS: A quick and dirty usability scale. Usability Evaluation in INdustry\/Taylor and Francis (1996)."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Cesar Cadena Luca Carlone Henry Carrillo Yasir Latif Davide Scaramuzza Jos\u00e9 Neira Ian Reid and John\u00a0J Leonard. 2016. Past present and future of simultaneous localization and mapping: Toward the robust-perception age. IEEE Transactions on robotics 32 6 (2016) 1309\u20131332.","DOI":"10.1109\/TRO.2016.2624754"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Eva Cetinic and James She. 2022. Understanding and Creating Art with AI: Review and Outlook. ACM Trans. Multimedia Comput. Commun. Appl. 18 2 Article 66 (feb 2022) 22\u00a0pages. 10.1145\/3475799","DOI":"10.1145\/3475799"},{"key":"e_1_3_3_3_20_2","volume-title":"European Conference on Computer Vision (ECCV)","author":"Chen Anpei","year":"2024","unstructured":"Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, and Andreas Geiger. 2024. LaRa: Efficient Large-Baseline Radiance Fields. In European Conference on Computer Vision (ECCV). Springer-Verlag, Berlin, Heidelberg."},{"key":"e_1_3_3_3_21_2","unstructured":"Jiangong Chen Xiaoyi Wu Tian Lan and Bin Li. 2025. LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2502.02441\u00a0[cs.MM] https:\/\/arxiv.org\/abs\/2502.02441"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02632"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474750"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","unstructured":"Erin Cherry and Celine Latulipe. 2014. Quantifying the Creativity Support of Digital Tools through the Creativity Support Index. ACM Trans. Comput.-Hum. Interact. 21 4 Article 21 (jun 2014) 25\u00a0pages. 10.1145\/2617588","DOI":"10.1145\/2617588"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Angela Dai Matthias Nie\u00dfner Michael Zollh\u00f6fer Shahram Izadi and Christian Theobalt. 2017. Bundlefusion: Real-time globally consistent 3d reconstruction using on-the-fly surface reintegration. ACM Transactions on Graphics (ToG) 36 4 (2017) 1.","DOI":"10.1145\/3072959.3126814"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642579"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415881"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.90"},{"key":"e_1_3_3_3_30_2","unstructured":"Cathy\u00a0Mengying Fang Krzysztof Zieli\u0144ski Pattie Maes Joe Paradiso Bruce Blumberg and Mikkel\u00a0Baun Kj\u00e6rgaard. 2024. Enabling Waypoint Generation for Collaborative Robots using LLMs and Mixed Reality. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.09308 (2024)."},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354978"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00078"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"crossref","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63 11 (2020) 139\u2013144.","DOI":"10.1145\/3422622"},{"key":"e_1_3_3_3_34_2","unstructured":"Google. 2024. ARCore. https:\/\/developers.google.com\/ar."},{"key":"e_1_3_3_3_35_2","unstructured":"Google. 2024. Build global-scale immersive location-based AR experiences with the ARCore Geospatial API. https:\/\/developers.google.com\/ar\/develop\/geospatial."},{"key":"e_1_3_3_3_36_2","unstructured":"Google Maps. 2024. Create and publish your own Street View imagery. https:\/\/www.google.com\/streetview\/contribute\/"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"e_1_3_3_3_38_2","unstructured":"Alicia Guo Shreya Sathyanarayanan Leijie Wang Jeffrey Heer and Amy Zhang. 2024. From pen to prompt: How creative writers integrate AI into their writing practice. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.03137 (2024)."},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"e_1_3_3_3_40_2","unstructured":"Yuze He Yushi Bai Matthieu Lin Wang Zhao Yubin Hu Jenny Sheng Ran Yi Juanzi Li and Yong-Jin Liu. 2023. T3Bench: Benchmarking Current Progress in Text-to-3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2310.02977\u00a0[cs.CV]"},{"key":"e_1_3_3_3_41_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_3_42_2","unstructured":"Yicong Hong Kai Zhang Jiuxiang Gu Sai Bi Yang Zhou Difan Liu Feng Liu Kalyan Sunkavalli Trung Bui and Hao Tan. 2023. Lrm: Large reconstruction model for single image to 3d. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.04400 (2023)."},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_44_2","volume-title":"Forty-first International Conference on Machine Learning","author":"Hu Ziniu","year":"2024","unstructured":"Ziniu Hu, Ahmet Iscen, Aashi Jain, Thomas Kipf, Yisong Yue, David\u00a0A Ross, Cordelia Schmid, and Alireza Fathi. 2024. SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=gAyzjHw2ml"},{"key":"e_1_3_3_3_45_2","unstructured":"Han Huang Fernanda De\u00a0La Torre Cathy\u00a0Mengying Fang Andrzej Banburski-Fahey Judith Amores and Jaron Lanier. 2024. Real-time Animation Generation and Control on Rigged Models via Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2310.17838\u00a0[cs.GR] https:\/\/arxiv.org\/abs\/2310.17838"},{"key":"e_1_3_3_3_46_2","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Huang Jiangyong","year":"2024","unstructured":"Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang. 2024. An Embodied Generalist Agent in 3D World. In Proceedings of the International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_3_47_2","unstructured":"IKEA. 2024. IKEA Place app launched to help people virtually place furniture at home. https:\/\/www.ikea.com\/global\/en\/newsroom\/innovation\/ikea-launches-ikea-place-a-new-app-that-allows-people-to-virtually-place-furniture-in-their-home-170912\/."},{"key":"e_1_3_3_3_48_2","unstructured":"Niantic Inc. 2024. Lightship ARDK. https:\/\/lightship.dev\/products\/ardk."},{"key":"e_1_3_3_3_49_2","unstructured":"Niantic Inc. 2024. Lightship VPS. https:\/\/lightship.dev\/products\/vps."},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Krishna Murthy Jatavallabhula Alihusein Kuwajerwala Qiao Gu Mohd Omama Tao Chen Shuang Li Ganesh Iyer Soroush Saryazdi Nikhil Keetha Ayush Tewari Joshua B. Tenenbaum Celso Miguel de Melo Madhava Krishna Liam Paull Florian Shkurti and Antonio Torralba. 2023. ConceptFusion: Open-set Multimodal 3D Mapping. Robotics: Science and Systems (RSS) (2023).","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3649127"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","unstructured":"Terence Karran. 2005. Pan\u2010European Grading Scales: Lessons from National Systems and the ECTS. Higher Education in Europe 30 1 (2005) 5\u201322. 10.1080\/03797720500087949 arXiv:10.1080\/03797720500087949","DOI":"10.1080\/03797720500087949"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01345"},{"key":"e_1_3_3_3_57_2","unstructured":"LEGO. 2024. New App brings LEGO\u00ae bricks to life. https:\/\/www.lego.com\/en-us\/aboutus\/news\/2019\/october\/lego-ar-studio."},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474774"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376160"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481287"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347945"},{"key":"e_1_3_3_3_62_2","unstructured":"Haohe Liu Zehua Chen Yi Yuan Xinhao Mei Xubo Liu Danilo Mandic Wenwu Wang and Mark\u00a0D. Plumbley. 2023. AudioLDM: Text-to-Audio Generation with Latent Diffusion Models. arxiv:https:\/\/arXiv.org\/abs\/2301.12503\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2301.12503"},{"key":"e_1_3_3_3_63_2","unstructured":"Minghua Liu Chao Xu Haian Jin Linghao Chen Mukund Varma\u00a0T Zexiang Xu and Hao Su. 2024. One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_64_2","unstructured":"Xianzheng Ma Yash Bhalgat Brandon Smart Shuai Chen Xinghui Li Jian Ding Jindong Gu Dave\u00a0Zhenyu Chen Songyou Peng Jia-Wang Bian et\u00a0al. 2024. When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.10255 (2024)."},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"crossref","unstructured":"Leland McInnes John Healy Steve Astels et\u00a0al. 2017. hdbscan: Hierarchical density based clustering. J. Open Source Softw. 2 11 (2017) 205.","DOI":"10.21105\/joss.00205"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","unstructured":"Michael Nebeling. 2022. XR tools and where they are taking us: characterizing the evolving research on augmented virtual and mixed reality prototyping and development tools. XRDS 29 1 (oct 2022) 32\u201338. 10.1145\/3558192","DOI":"10.1145\/3558192"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539794"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2011.6092378"},{"key":"e_1_3_3_3_70_2","unstructured":"Niantic. 2024. Catch Pok\u00e9mon. Find your buddy! https:\/\/pokemongolive.com."},{"key":"e_1_3_3_3_71_2","unstructured":"Niantic. 2024. Meshing. https:\/\/lightship.dev\/docs\/ardk\/features\/meshing\/"},{"key":"e_1_3_3_3_72_2","unstructured":"Niantic. 2024. Share your world in 3D with Scaniverse 4. https:\/\/scaniverse.com"},{"key":"e_1_3_3_3_73_2","unstructured":"Niantic. 2025. Niantic VPS. https:\/\/www.nianticspatial.com\/products\/visual-positioning-system."},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0I. Norton Daniel Mochon and Dan Ariely. 2012. The IKEA effect: When labor leads to love. Journal of Consumer Psychology 22 3 (2012) 453\u2013460. 10.1016\/j.jcps.2011.08.002","DOI":"10.1016\/j.jcps.2011.08.002"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676361"},{"key":"e_1_3_3_3_76_2","unstructured":"OpenAI. 2024. Editing your images with DALL\u00b7E. https:\/\/help.openai.com\/en\/articles\/9055440-editing-your-images-with-dall-e."},{"key":"e_1_3_3_3_77_2","unstructured":"OpenAI. 2024. GPT-4o mini: advancing cost-efficient intelligence. https:\/\/openai.com\/index\/gpt-4o-mini-advancing-cost-efficient-intelligence\/."},{"key":"e_1_3_3_3_78_2","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"e_1_3_3_3_79_2","unstructured":"OpenAI. 2024. Introducing Whisper. https:\/\/openai.com\/index\/whisper\/."},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"e_1_3_3_3_81_2","unstructured":"Polycam. 2024. Polycam: 3D scanning platform. https:\/\/poly.cam"},{"key":"e_1_3_3_3_82_2","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_3"},{"key":"e_1_3_3_3_84_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_3_85_2","unstructured":"Nikhil Raina Guruprasad Somasundaram Kang Zheng Sagar Miglani Steve Saarinen Jeff Meissner Mark Schwesinger Luis Pesqueira Ishita Prasad Edward Miller Prince Gupta Mingfei Yan Richard Newcombe Carl Ren and Omkar\u00a0M Parkhi. 2023. EgoBlur: Responsible Innovation in Aria. arxiv:https:\/\/arXiv.org\/abs\/2308.13093\u00a0[cs.CV]"},{"key":"e_1_3_3_3_86_2","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_3_3_87_2","first-page":"8821","volume-title":"International conference on machine learning","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, JMLR.org, New York, NY, USA, 8821\u20138831."},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"crossref","unstructured":"Antoni Rosinol Arjun Gupta Marcus Abate Jingnan Shi and Luca Carlone. 2020. 3D dynamic scene graphs: Actionable spatial perception with places objects and humans. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.06289 (2020).","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"e_1_3_3_3_90_2","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_3_91_2","unstructured":"Axel Sauer Dominik Lorenz Andreas Blattmann and Robin Rombach. 2023. Adversarial diffusion distillation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.17042 (2023)."},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_1"},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"e_1_3_3_3_94_2","unstructured":"Yichun Shi Peng Wang Jianglong Ye Long Mai Kejie Li and Xiao Yang. 2023. MVDream: Multi-view Diffusion for 3D Generation. arXiv:https:\/\/arXiv.org\/abs\/2308.16512 (2023)."},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","unstructured":"Ben Shneiderman. 2020. Human-Centered Artificial Intelligence: Reliable Safe & Trustworthy. International Journal of Human\u2013Computer Interaction 36 6 (2020) 495\u2013504. 10.1080\/10447318.2020.1741118 arXiv:10.1080\/10447318.2020.1741118","DOI":"10.1080\/10447318.2020.1741118"},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3636283"},{"key":"e_1_3_3_3_97_2","unstructured":"SnapAR. 2024. Your Creativity Powered by Lens Studio. https:\/\/ar.snap.com\/lens-studio."},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00091"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676406"},{"key":"e_1_3_3_3_100_2","unstructured":"Chunyi Sun Junlin Han Weijian Deng Xinlong Wang Zishan Qin and Stephen Gould. 2023. 3d-gpt: Procedural 3d modeling with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.12945 (2023)."},{"key":"e_1_3_3_3_101_2","doi-asserted-by":"publisher","unstructured":"Lu Sun Stone Tao Junjie Hu and Steven\u00a0P. Dow. 2024. MetaWriter: Exploring the Potential and Perils of AI Writing Support in Scientific Peer Review. Proc. ACM Hum.-Comput. Interact. 8 CSCW1 Article 94 (apr 2024) 32\u00a0pages. 10.1145\/3637371","DOI":"10.1145\/3637371"},{"key":"e_1_3_3_3_102_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Takmaz Ay\u00e7a","year":"2023","unstructured":"Ay\u00e7a Takmaz, Elisabetta Fedele, Robert\u00a0W. Sumner, Marc Pollefeys, Federico Tombari, and Francis Engelmann. 2023. OpenMask3D: Open-Vocabulary 3D Instance Segmentation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_3_103_2","unstructured":"Jiaxiang Tang Jiawei Ren Hang Zhou Ziwei Liu and Gang Zeng. 2023. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16653 (2023)."},{"key":"e_1_3_3_3_104_2","unstructured":"Torch. 2024. Torch. Tap the Power of 3D. https:\/\/torch-website.webflow.io\/tour-the-app."},{"key":"e_1_3_3_3_105_2","unstructured":"Unity. 2024. ARFoundation. https:\/\/docs.unity3d.com\/Packages\/com.unity.xr.arfoundation@5.1\/manual\/index.html."},{"key":"e_1_3_3_3_106_2","unstructured":"Unity. 2024. Go Create with Unity. https:\/\/unity.com."},{"key":"e_1_3_3_3_107_2","unstructured":"Unity. 2024. Unity Mars. https:\/\/unity.com\/products\/unity-mars."},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714312"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642271"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"e_1_3_3_3_111_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580776"},{"key":"e_1_3_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642772"},{"key":"e_1_3_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"e_1_3_3_3_115_2","doi-asserted-by":"crossref","unstructured":"Jianfeng Xiang Zelong Lv Sicheng Xu Yu Deng Ruicheng Wang Bowen Zhang Dong Chen Xin Tong and Jiaolong Yang. 2024. Structured 3D Latents for Scalable and Versatile 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2412.01506\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.01506","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_3_116_2","doi-asserted-by":"crossref","unstructured":"Jianfeng Xiang Zelong Lv Sicheng Xu Yu Deng Ruicheng Wang Bowen Zhang Dong Chen Xin Tong and Jiaolong Yang. 2025. Structured 3D Latents for Scalable and Versatile 3D Generation. arxiv:https:\/\/arXiv.org\/abs\/2412.01506\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2412.01506","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_18"},{"key":"e_1_3_3_3_118_2","unstructured":"Jiale Xu Weihao Cheng Yiming Gao Xintao Wang Shenghua Gao and Ying Shan. 2024. Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.07191 (2024)."},{"key":"e_1_3_3_3_119_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"e_1_3_3_3_120_2","unstructured":"Lihe Yang Bingyi Kang Zilong Huang Zhen Zhao Xiaogang Xu Jiashi Feng and Hengshuang Zhao. 2024. Depth Anything V2. arXiv:https:\/\/arXiv.org\/abs\/2406.09414 (2024)."},{"key":"e_1_3_3_3_121_2","doi-asserted-by":"publisher","unstructured":"Hui Ye Kin\u00a0Chung Kwan Wanchao Su and Hongbo Fu. 2020. ARAnimator: in-situ character animation in mobile AR with user-defined motion gestures. ACM Trans. Graph. 39 4 Article 83 (aug 2020) 12\u00a0pages. 10.1145\/3386569.3392404","DOI":"10.1145\/3386569.3392404"},{"key":"e_1_3_3_3_122_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676451"},{"key":"e_1_3_3_3_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_124_2","unstructured":"Youcai Zhang Xinyu Huang Jinyu Ma Zhaoyang Li Zhaochuan Luo Yanchun Xie Yuzhuo Qin Tong Luo Yaqian Li Shilong Liu et\u00a0al. 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.03514 (2023)."},{"key":"e_1_3_3_3_125_2","unstructured":"Zibo Zhao Zeqiang Lai Qingxiang Lin Yunfei Zhao Haolin Liu Shuhui Yang Yifei Feng Mingxin Yang Sheng Zhang Xianghui Yang Huiwen Shi Sicong Liu Junta Wu Yihang Lian Fan Yang Ruining Tang Zebin He Xinzhou Wang Jian Liu Xuhui Zuo Zhuo Chen Biwen Lei Haohan Weng Jing Xu Yiling Zhu Xinhai Liu Lixin Xu Changrong Hu Shaoxiong Yang Song Zhang Yang Liu Tianyu Huang Lifu Wang Jihong Zhang Meng Chen Liang Dong Yiwen Jia Yulin Cai Jiaao Yu Yixuan Tang Hao Zhang Zheng Ye Peng He Runzhou Wu Chao Zhang Yonghao Tan Jie Xiao Yangyu Tao Jianchen Zhu Jinbao Xue Kai Liu Chongqing Zhao Xinming Wu Zhichao Hu Lei Qin Jianbing Peng Zhan Li Minghui Chen Xipeng Zhang Lin Niu Paige Wang Yingkai Wang Haozhao Kuang Zhongyi Fan Xu Zheng Weihao Zhuang YingPing He Tian Liu Yong Yang Di Wang Yuhong Liu Jie Jiang Jingwei Huang and Chunchao Guo. 2025. Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation. arxiv:https:\/\/arXiv.org\/abs\/2501.12202\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2501.12202"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:02:44Z","timestamp":1759010564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":124,"alternative-id":["10.1145\/3746059.3747635","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747635","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}