{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:48Z","timestamp":1765340088674,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"Culture, Sports and Tourism R&D Program through the Korea Creative Content Agency grant funded by the Ministry of Culture, Sports and Tourism in 2025 (Project Name: Development of AI-based image expansion and service technology for high-resolution (8K\/16K) service of performance contents)","award":["RS-2024-00395886"],"award-info":[{"award-number":["RS-2024-00395886"]}]},{"name":"The MSIT (Ministry of Science and ICT), Korea, under the Graduate School of Metaverse Convergence support program supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation)","award":["IITP-2025-RS-2024-00430997"],"award-info":[{"award-number":["IITP-2025-RS-2024-00430997"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754563","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"9206-9215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VRMusicStage: A System for Converting Fixed-Camera Music Stage Videos into Immersive VR Content"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7173-373X","authenticated-orcid":false,"given":"Seungkyu","family":"Leem","sequence":"first","affiliation":[{"name":"Department of Metaverse and Culture Contents, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4729-0805","authenticated-orcid":false,"given":"Seokhyun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Metaverse and Culture Contents, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2671-8593","authenticated-orcid":false,"given":"Yeonho","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Metaverse and Culture Contents, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6342-6947","authenticated-orcid":false,"given":"Yoonjae","family":"Lee","sequence":"additional","affiliation":[{"name":"Korean Broadcasting System, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3471-4848","authenticated-orcid":false,"given":"Jungjin","family":"Lee","sequence":"additional","affiliation":[{"name":"The Global School of Media, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"538","article-title":"Disturbance and plausibility in a virtual rock concert: A pilot study. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR)","author":"Beacco Alejandro","year":"2021","unstructured":"Alejandro Beacco, Ramon Oliva, Carlos Cabreira, Jaime Gallego, and Mel Slater. 2021. Disturbance and plausibility in a virtual rock concert: A pilot study. In 2021 IEEE Virtual Reality and 3D User Interfaces (VR). IEEE, 538-545.","journal-title":"IEEE"},{"key":"e_1_3_2_2_2_1","volume-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288","author":"Bhat Shariq Farooq","year":"2023","unstructured":"Shariq Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, and Matthias M\u00fcller. 2023. Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)."},{"key":"e_1_3_2_2_3_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_2_4_1","unstructured":"Lies Bouckaert. 2021. Virtual reality as new concert space. Ph.D. Dissertation. Ph. D. Dissertation. PhD thesis UNIVERSITEIT GENT BELGIUM."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00776"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"volume-title":"Civitai: The Home of Open-Source Generative AI. https:\/\/civitai.com\/ Retrieved","year":"2025","key":"e_1_3_2_2_8_1","unstructured":"Civitai. 2025. Civitai: The Home of Open-Source Generative AI. https:\/\/civitai.com\/ Retrieved Apr. 09, 2025 from"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00084"},{"key":"e_1_3_2_2_10_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780-8794."},{"key":"e_1_3_2_2_11_1","volume-title":"Forty-first international conference on machine learning.","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al., 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612478"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_2_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952541"},{"key":"e_1_3_2_2_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"volume-title":"Huggingface - The AI community building the future., https:\/\/huggingface.co\/ Retrieved","year":"2025","key":"e_1_3_2_2_18_1","unstructured":"Huggingface. 2025. Huggingface - The AI community building the future., https:\/\/huggingface.co\/ Retrieved Apr. 09, 2025 from"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548347"},{"key":"e_1_3_2_2_20_1","unstructured":"Diederik P Kingma Max Welling et al. 2013. Auto-encoding variational bayes."},{"key":"e_1_3_2_2_21_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"Rich360: optimized spherical representation from structured panoramic camera arrays","volume":"35","author":"Lee Jungjin","year":"2016","unstructured":"Jungjin Lee, Bumki Kim, Kyehyun Kim, Younghui Kim, and Junyong Noh. 2016. Rich360: optimized spherical representation from structured panoramic camera arrays. ACM Transactions on Graphics (TOG), Vol. 35, 4 (2016), 1-11.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196492"},{"volume-title":"sd-webui-controlnet. https:\/\/github.com\/Mikubill\/sd-webui-controlnet Retrieved","year":"2025","key":"e_1_3_2_2_24_1","unstructured":"Mikubill. 2023. sd-webui-controlnet. https:\/\/github.com\/Mikubill\/sd-webui-controlnet Retrieved Apr. 09, 2025 from"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3134555"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-023-00814-y"},{"volume-title":"clip-interrogator. https:\/\/github.com\/pharmapsychotic\/clip-interrogator Retrieved","year":"2025","key":"e_1_3_2_2_27_1","unstructured":"pharmapsychotic. 2022. clip-interrogator. https:\/\/github.com\/pharmapsychotic\/clip-interrogator Retrieved Apr. 09, 2025 from"},{"key":"e_1_3_2_2_28_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3317697.3323361"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_33_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al., 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278-25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2023.107910"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2019.02.001"},{"key":"e_1_3_2_2_36_1","unstructured":"Murray Stassen. 2022. VR concert startup AmazeVR raises $17m with Korea's CJ Entertainment joining as strategic investor. https:\/\/www.musicbusinessworldwide.com\/vr-concert-startup-amazevr-raises-17m-with-koreas-cj-entertainment-joining-as-strategic-investor\/ Retrieved Apr. 09 2025 from"},{"key":"e_1_3_2_2_37_1","volume-title":"Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference","author":"Teed Zachary","year":"2020","unstructured":"Zachary Teed and Jia Deng. 2020. Raft: Recurrent all-pairs field transforms for optical flow. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part II 16. Springer, 402-419."},{"key":"e_1_3_2_2_38_1","volume-title":"Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly.","author":"Unterthiner Thomas","year":"2018","unstructured":"Thomas Unterthiner, Sjoerd Van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)."},{"key":"e_1_3_2_2_39_1","volume-title":"The 'lonely raver': music livestreams during COVID-19 as a hotline to collective consciousness? European societies","author":"Vandenberg Femke","year":"2021","unstructured":"Femke Vandenberg, Micha\u00ebl Berghman, and Julian Schaap. 2021. The 'lonely raver': music livestreams during COVID-19 as a hotline to collective consciousness? European societies, Vol. 23, S1 (2021), S141-S152."},{"key":"e_1_3_2_2_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_41_1","volume-title":"Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation. arXiv preprint arXiv:2403.13745","author":"Wang Fu-Yun","year":"2024","unstructured":"Fu-Yun Wang, Xiaoshi Wu, Zhaoyang Huang, Xiaoyu Shi, Dazhong Shen, Guanglu Song, Yu Liu, and Hongsheng Li. 2024. Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation. arXiv preprint arXiv:2403.13745 (2024)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"e_1_3_2_2_43_1","volume-title":"Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis. arXiv preprint arXiv:2207.09814","author":"Wu Chenfei","year":"2022","unstructured":"Chenfei Wu, Jian Liang, Xiaowei Hu, Zhe Gan, Jianfeng Wang, Lijuan Wang, Zicheng Liu, Yuejian Fang, and Nan Duan. 2022. Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis. arXiv preprint arXiv:2207.09814 (2022)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR50242.2020.00083"},{"key":"e_1_3_2_2_45_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"volume-title":"Search results for ''K-Choreo 8K''. https:\/\/www.youtube.com\/results?search_query=K-Choreo8K Retrieved","year":"2025","key":"e_1_3_2_2_46_1","unstructured":"Youtube. 2025. Search results for ''K-Choreo 8K''. https:\/\/www.youtube.com\/results?search_query=K-Choreo8K Retrieved Apr. 09, 2025 from"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_2_48_1","volume-title":"Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428","author":"Zhao Shengyu","year":"2021","unstructured":"Shengyu Zhao, Jonathan Cui, Yilun Sheng, Yue Dong, Xiao Liang, Eric I Chang, and Yan Xu. 2021. Large scale image completion via co-modulated generative adversarial networks. arXiv preprint arXiv:2103.10428 (2021)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:11:01Z","timestamp":1765339861000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3754563","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754563","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}