{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:21:50Z","timestamp":1765308110665,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755082","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"9724-9732","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CP3: Customizable 3D Pop-Out Effect Creation for Immersive Content Using Multimodal Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6796-6043","authenticated-orcid":false,"given":"Zezhou","family":"Chen","sequence":"first","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2430-6944","authenticated-orcid":false,"given":"Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6697-3220","authenticated-orcid":false,"given":"Huan","family":"Hu","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2492-403X","authenticated-orcid":false,"given":"Xiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9720-7156","authenticated-orcid":false,"given":"Zipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1267-0277","authenticated-orcid":false,"given":"Zhaoxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Beijing Key Laboratory of Science Fiction Audio and Video Intelligent Processing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1171-0281","authenticated-orcid":false,"given":"Kai","family":"Wang","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4308-7049","authenticated-orcid":false,"given":"Shiguo","family":"Lian","sequence":"additional","affiliation":[{"name":"Data Science & Artificial Intelligence Research Institute, China Unicom, Beijing, China and Unicom Data Intelligence, China Unicom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Immersity AI. 2024. The AI platform converting images and videos into 3D. https:\/\/www.immersity.ai\/ Accessed: 2024-11-15."},{"key":"e_1_3_2_1_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. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_5_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et al. 2023b. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840","author":"Chen Weifeng","year":"2023","unstructured":"Weifeng Chen, Yatai Ji, Jie Wu, Hefeng Wu, Pan Xie, Jiashi Li, Xin Xia, Xuefeng Xiao, and Liang Lin. 2023a. Control-a-video: Controllable text-to-video generation with diffusion models. arXiv preprint arXiv:2305.13840 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Fridman Rafail","year":"2024","unstructured":"Rafail Fridman, Amit Abecasis, Yoni Kasten, and Tali Dekel. 2024. Scenescape: Text-driven consistent scene generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_8_1","unstructured":"Jonathan Ho William Chan Chitwan Saharia Jay Whang Ruiqi Gao Alexey Gritsenko Diederik P Kingma Ben Poole Mohammad Norouzi David J Fleet et al. 2022. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)."},{"key":"e_1_3_2_1_9_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_1_10_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"e_1_3_2_1_12_1","volume-title":"Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. Advances in neural information processing systems, Vol. 35 (2022), 26565-26577."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_2_1_15_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Shilong Liu Zhaoyang Zeng Tianhe Ren Feng Li Hao Zhang Jie Yang Qing Jiang Chunyuan Li Jianwei Yang Hang Su et al. 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov I","year":"2017","unstructured":"I Loshchilov. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"e_1_3_2_1_20_1","first-page":"18481","article-title":"Revideo: Remake a video with motion and content control","volume":"37","author":"Mou Chong","year":"2024","unstructured":"Chong Mou, Mingdeng Cao, Xintao Wang, Zhaoyang Zhang, Ying Shan, and Jian Zhang. 2024. Revideo: Remake a video with motion and content control. Advances in Neural Information Processing Systems, Vol. 37 (2024), 18481-18505.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","unstructured":"Owl3D. 2024. AI-powered 2D to 3D conversion software. https:\/\/www.owl3d.com\/ Accessed: 2024-11-15."},{"key":"e_1_3_2_1_22_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_23_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_1_24_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_25_1","unstructured":"Nikhila Ravi Valentin Gabeur Yuan-Ting Hu Ronghang Hu Chaitanya Ryali Tengyu Ma Haitham Khedr Roman R\u00e4dle Chloe Rolland Laura Gustafson et al. 2024. Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_27_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_28_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103","author":"Wang Yaohui","year":"2023","unstructured":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, et al., 2023. Lavie: High-quality video generation with cascaded latent diffusion models. arXiv preprint arXiv:2309.15103 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_31_1","volume-title":"Depth Anything V2. arXiv preprint arXiv:2406.09414","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything V2. arXiv preprint arXiv:2406.09414 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2024","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2024. Show-1: Marrying pixel and latent diffusion models for text-to-video generation. International Journal of Computer Vision (2024), 1-15."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"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\/3746027.3755082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:06Z","timestamp":1765308006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":33,"alternative-id":["10.1145\/3746027.3755082","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755082","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"}}]}}