{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:27Z","timestamp":1755823287253,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Applied Basic Research Foundation","award":["2021A1515011584 and 2023A1515012956"],"award-info":[{"award-number":["2021A1515011584 and 2023A1515012956"]}]},{"name":"the National Natural Science Foundation of China","award":["U22B2035 and 62271323"],"award-info":[{"award-number":["U22B2035 and 62271323"]}]},{"name":"Shenzhen R\\&D Program","award":["JCYJ20220531102408020 and JCYJ20200109105008228"],"award-info":[{"award-number":["JCYJ20220531102408020 and JCYJ20200109105008228"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612356","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"2635-2643","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0352-4075","authenticated-orcid":false,"given":"Xujie","family":"Kang","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6293-5464","authenticated-orcid":false,"given":"Kanglin","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6867-6937","authenticated-orcid":false,"given":"Jiang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwestern University of Finance and Econom, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5702-1927","authenticated-orcid":false,"given":"Yuanhao","family":"Gong","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5877-5648","authenticated-orcid":false,"given":"Guoping","family":"Qiu","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"volume-title":"Neural scene representation and rendering. Science 360, 6394","year":"2018","key":"e_1_3_2_1_1_1","unstructured":"2018. Neural scene representation and rendering. Science 360, 6394 (2018), 1204--1210."},{"key":"e_1_3_2_1_2_1","volume-title":"Andreas Geiger, and Carsten Rother.","author":"Alhaija Hassan Abu","year":"2019","unstructured":"Hassan Abu Alhaija, Siva Karthik Mustikovela, Andreas Geiger, and Carsten Rother. 2019. Geometric image synthesis. In Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2-6, 2018, Revised Selected Papers, Part VI 14. Springer, 85--100."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_36"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237269"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"e_1_3_2_1_7_1","volume-title":"Woods RE: Digital Image Processing. upper saddle river nj pearson\/prentice hall","author":"Gonzalez R.","year":"2002","unstructured":"R. Gonzalez. 2002. Woods RE: Digital Image Processing. upper saddle river nj pearson\/prentice hall (2002)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00838"},{"key":"e_1_3_2_1_11_1","first-page":"202","article-title":"Disentangled representation learning generative adversarial network for pose-invariant face recognition","volume":"16","author":"Liu Xiaoming","year":"2020","unstructured":"Xiaoming Liu, Luan Quoc Tran, and Xi Yin. 2020. Disentangled representation learning generative adversarial network for pose-invariant face recognition. US Patent App. 16\/648,202.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00459"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_14_1","volume-title":"Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957","author":"Miyato Takeru","year":"2018","unstructured":"Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. 2018. Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3532833.3538678"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"T M\u00fcller A. Evans C. Schied and A. Keller. 2022. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding. arXiv e-prints (2022).","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7588--7597","author":"Nguyen-Phuoc Thu","year":"2019","unstructured":"Thu Nguyen-Phuoc, Chuan Li, Lucas Theis, Christian Richardt, and Yong-Liang Yang. 2019. Hologan: Unsupervised learning of 3d representations from natural images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 7588--7597."},{"key":"e_1_3_2_1_18_1","unstructured":"A. Noguchi and T. Harada. 2019. RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis."},{"key":"e_1_3_2_1_19_1","volume-title":"Perspectivenet: A scene-consistent image generator for new view synthesis in real indoor environments. Advances in Neural Information Processing Systems 32","author":"Novotny David","year":"2019","unstructured":"David Novotny, Ben Graham, and Jeremy Reizenstein. 2019. Perspectivenet: A scene-consistent image generator for new view synthesis in real indoor environments. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00463"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00463"},{"volume-title":"Computer Graphics Forum","author":"Rainer Gilles","key":"e_1_3_2_1_22_1","unstructured":"Gilles Rainer, Abhijeet Ghosh, Wenzel Jakob, and Tim Weyrich. 2020. Unified neural encoding of BTFs. In Computer Graphics Forum, Vol. 39. Wiley Online Library, 167--178."},{"volume-title":"Computer Graphics Forum","author":"Rainer Gilles","key":"e_1_3_2_1_23_1","unstructured":"Gilles Rainer, Wenzel Jakob, Abhijeet Ghosh, and Tim Weyrich. 2019. Neural BTF compression and interpolation. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 235--244."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462009"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Y. Shen P. Luo J. Yan X. Wang and X. Tang. 2018. FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis. IEEE (2018).","DOI":"10.1109\/CVPR.2018.00092"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"e_1_3_2_1_28_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"V. Sitzmann J. Thies F. Heide M Nie\u00dfner G. Wetzstein and M Zollh\u00f6fer. 2018. DeepVoxels: Learning Persistent 3D Feature Embeddings. (2018).","DOI":"10.1109\/CVPR.2019.00254"},{"key":"e_1_3_2_1_30_1","volume-title":"Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa.","author":"Tancik Matthew","year":"2023","unstructured":"Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Justin Kerr, Terrance Wang, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David McAllister, and Angjoo Kanazawa. 2023. Nerfstudio: A Modular Framework for Neural Radiance Field Development. arXiv preprint arXiv:2302.04264 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Abhinav Gupta XiaolongWang","year":"2016","unstructured":"XiaolongWang and Abhinav Gupta. 2016. Generative image modeling using style and structure adversarial networks. In Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14. Springer, 318--335."},{"key":"e_1_3_2_1_32_1","volume-title":"Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"X. Zhang P. P. Srinivasan B. Deng P. Debevec W. T. Freeman and J. T. Barron. 2021. NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination. (2021).","DOI":"10.1145\/3478513.3480496"},{"key":"e_1_3_2_1_34_1","volume-title":"Visual object networks: Image generation with disentangled 3D representations. Advances in neural information processing systems 31","author":"Zhu Jun-Yan","year":"2018","unstructured":"Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Josh Tenenbaum, and Bill Freeman. 2018. Visual object networks: Image generation with disentangled 3D representations. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Visual object networks: Image generation with disentangled 3D representations. Advances in neural information processing systems 31","author":"Zhu Jun-Yan","year":"2018","unstructured":"Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Josh Tenenbaum, and Bill Freeman. 2018. Visual object networks: Image generation with disentangled 3D representations. Advances in neural information processing systems 31 (2018)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612356","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:11Z","timestamp":1755820811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":35,"alternative-id":["10.1145\/3581783.3612356","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612356","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}