{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:58:06Z","timestamp":1785488286420,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3774521.3774603","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T07:34:24Z","timestamp":1785483264000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GeMR : Multi-modal Interactive 3D Scene Composition In XR"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4861-4767","authenticated-orcid":false,"given":"Raghav","family":"Mittal","sequence":"first","affiliation":[{"name":"TCS Research, New Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9217-4248","authenticated-orcid":false,"given":"Lokender","family":"Tiwari","sequence":"additional","affiliation":[{"name":"TCS Research, New Delhi, Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2482-8441","authenticated-orcid":false,"given":"Shivam Ashok","family":"Shukla","sequence":"additional","affiliation":[{"name":"TCS Research, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7174-227X","authenticated-orcid":false,"given":"Mritunjoy","family":"Halder","sequence":"additional","affiliation":[{"name":"TCS Research, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9291-5889","authenticated-orcid":false,"given":"Brojeshwar","family":"Bhowmick","sequence":"additional","affiliation":[{"name":"TCS Research, Kolkata, West Bengal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Amazon Web Services. 2025. What is Service-Oriented Architecture?https:\/\/aws.amazon.com\/what-is\/service-oriented-architecture\/ Accessed: 2025-07-27."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Rahul Arora and Karan Singh. 2021. Mid-air drawing of curves on 3d surfaces in virtual reality. ACM Transactions on Graphics (TOG) 40 3 (2021) 1\u201317.","DOI":"10.1145\/3459090"},{"key":"e_1_3_3_2_4_2","unstructured":"Autodesk. 2025. Maya. Retrieved August 8 2025 from https:\/\/en.wikipedia.org\/wiki\/Autodesk_Maya"},{"key":"e_1_3_3_2_5_2","unstructured":"Aaron Bangor Philip\u00a0T. Kortum and James\u00a0T. Miller. 2009. Determining what individual SUS scores mean: adding an adjective rating scale. Journal of Usability Studies archive 4 (2009) 114\u2013123. https:\/\/api.semanticscholar.org\/CorpusID:7812093"},{"key":"e_1_3_3_2_6_2","unstructured":"Blender. 2025. Blender. Retrieved August 7 2025 from https:\/\/en.wikipedia.org\/wiki\/Blender_(software)"},{"key":"e_1_3_3_2_7_2","unstructured":"John Brooke et\u00a0al. 1996. SUS-A quick and dirty usability scale. Usability evaluation in industry 189 194 (1996) 4\u20137."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","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. IEEE Transactions on Visualization & Computer Graphics 31 05 (May 2025) 2715\u20132724. 10.1109\/TVCG.2025.3549549","DOI":"10.1109\/TVCG.2025.3549549"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01264"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Tianrun Chen Chaotao Ding Lanyun Zhu Ying Zang Yiyi Liao Zejian Li and Lingyun Sun. 2024. Reality3DSketch: Rapid 3D Modeling of Objects From Single Freehand Sketches. Trans. Multi. 26 (Jan. 2024) 4859\u20134870. 10.1109\/TMM.2023.3327533","DOI":"10.1109\/TMM.2023.3327533"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02127"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3452918.3458806"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Sandra\u00a0G. Hart. 2006. Nasa-Task Load Index (NASA-TLX); 20 Years Later. Proceedings of the Human Factors and Ergonomics Society Annual Meeting 50 9 (2006) 904\u2013908. 10.1177\/154193120605000909 arXiv:10.1177\/154193120605000909","DOI":"10.1177\/154193120605000909"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_3_2_17_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."},{"key":"e_1_3_3_2_18_2","unstructured":"Black\u00a0Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Minkyung Lee Mark Billinghurst Woonhyuk Baek Richard Green and Woontack Woo. 2013. A usability study of multimodal input in an augmented reality environment. Virtual Real. 17 4 (Nov. 2013) 293\u2013305. 10.1007\/s10055-013-0230-0","DOI":"10.1007\/s10055-013-0230-0"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687621"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00050"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00018"},{"key":"e_1_3_3_2_23_2","unstructured":"Maxon. 2025. ZBrush. Retrieved August 7 2025 from https:\/\/en.wikipedia.org\/wiki\/ZBrush"},{"key":"e_1_3_3_2_24_2","unstructured":"Meta Horizon Developer Documentation. 2025. Voice SDK Overview (Unity). https:\/\/developers.meta.com\/horizon\/documentation\/unity\/voice-sdk-overview\/. Accessed: 2025-07-27."},{"key":"e_1_3_3_2_25_2","unstructured":"OpenAI. 2025. OpenAI Platform Documentation: Overview. https:\/\/platform.openai.com\/docs\/overview. Accessed: 2025-07-27."},{"key":"e_1_3_3_2_26_2","unstructured":"Charles\u00a0Ruizhongtai Qi Li Yi Hao Su and Leonidas\u00a0J Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_27_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Tao Xu Greg Brockman Christine McLeavey and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arxiv:https:\/\/arXiv.org\/abs\/2212.04356\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2212.04356"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","unstructured":"Fatema Rahimi Abolghasem Sadeghi-Niaraki and Soo-Mi Choi. 2025. Generative AI Meets Virtual Reality: A Comprehensive Survey on Applications Challenges and Future Direction. IEEE Access 13 (2025) 94893\u201394909. 10.1109\/ACCESS.2025.3574779","DOI":"10.1109\/ACCESS.2025.3574779"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591503"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Somaiieh Rokhsaritalemi Abolghasem Sadeghi-Niaraki and Soo-Mi Choi. 2020. A Review on Mixed Reality: Current Trends Challenges and Prospects. Applied Sciences 10 2 (2020). 10.3390\/app10020636","DOI":"10.3390\/app10020636"},{"key":"e_1_3_3_2_31_2","unstructured":"Aditya Sanghi Pradeep\u00a0Kumar Jayaraman Arianna Rampini Joseph Lambourne Hooman Shayani Evan Atherton and Saeid\u00a0Asgari Taghanaki. 2023. Sketch-a-shape: Zero-shot sketch-to-3d shape generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.03869 (2023)."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICAT57735.2023.10263706"},{"key":"e_1_3_3_2_33_2","unstructured":"Jiaxiang Tang Ruijie Lu Xiaokang Chen Xiang Wen Gang Zeng and Ziwei Liu. 2024. Intex: Interactive text-to-texture synthesis via unified depth-aware inpainting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.11878 (2024)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/AIxVR63409.2025.00052"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298797"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/VRW62533.2024.00388"},{"key":"e_1_3_3_2_37_2","first-page":"1912","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1912\u20131920."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"e_1_3_3_2_39_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_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00477"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Xin Yu Ze Yuan Yuan-Chen Guo Ying-Tian Liu Jianhui Liu Yangguang Li Yan-Pei Cao Ding Liang and Xiaojuan Qi. 2024. Texgen: a generative diffusion model for mesh textures. ACM Transactions on Graphics (TOG) 43 6 (2024) 1\u201314.","DOI":"10.1145\/3687909"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676451"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Yuqing Zhang Yuan Liu Zhiyu Xie Lei Yang Zhongyuan Liu Mengzhou Yang Runze Zhang Qilong Kou Cheng Lin Wenping Wang et\u00a0al. 2024. Dreammat: High-quality pbr material generation with geometry-and light-aware diffusion models. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201318.","DOI":"10.1145\/3658170"},{"key":"e_1_3_3_2_46_2","unstructured":"Zibo Zhao Zeqiang Lai Qingxiang Lin Yunfei Zhao Haolin Liu Shuhui Yang Yifei Feng Mingxin Yang Sheng Zhang Xianghui Yang et\u00a0al. 2025. Hunyuan3d 2.0: Scaling diffusion models for high resolution textured 3d assets generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12202 (2025)."}],"event":{"name":"ICVGIP 2025: Indian Conference on Computer Vision, Graphics, and Image Processing","location":"Mandi Himachal Pradesh India","acronym":"ICVGIP 2025"},"container-title":["Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774521.3774603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:07:57Z","timestamp":1785485277000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774521.3774603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":45,"alternative-id":["10.1145\/3774521.3774603","10.1145\/3774521"],"URL":"https:\/\/doi.org\/10.1145\/3774521.3774603","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-07-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}