{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:01:08Z","timestamp":1765310468098,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755121","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"7795-7804","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CaDGS: Modeling Inter-Gaussian Mutual Information for Dynamic Novel View Synthesis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2038-6540","authenticated-orcid":false,"given":"Yunlong","family":"Zhao","sequence":"first","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2740-8025","authenticated-orcid":false,"given":"Xiaoheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7892-7911","authenticated-orcid":false,"given":"Zhuohua","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3495-5257","authenticated-orcid":false,"given":"Feng","family":"Yang","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4756-0609","authenticated-orcid":false,"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8962-540X","authenticated-orcid":false,"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[{"name":"The University of Nottingham Ningbo China, Ningbo, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1964-0430","authenticated-orcid":false,"given":"Shan","family":"You","sequence":"additional","affiliation":[{"name":"Sensetime Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9863-5404","authenticated-orcid":false,"given":"Xiu","family":"Su","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01594"},{"key":"e_1_3_2_1_2_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer Normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_3_1","volume-title":"European Conference on Computer Vision. Springer, 321--335","author":"Bae Jeongmin","year":"2024","unstructured":"Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, and Youngjung Uh. 2024. Per-gaussian embedding-based deformation for deformable 3d gaussian splatting. In European Conference on Computer Vision. Springer, 321--335."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. 531--540","author":"Belghazi Mohamed Ishmael","year":"2018","unstructured":"Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, and Devon Hjelm. 2018. Mutual information neural estimation. In International Conference on Machine Learning. 531--540."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"e_1_3_2_1_10_1","first-page":"135","article-title":"Informative viewpoint selection for 3D scene understanding","volume":"35","author":"Chen Kai","year":"2016","unstructured":"Kai Chen, Yu-Kun Lai, Yong-Jin Wu, Ralph Martin, and Shi-Min Hu. 2016. Informative viewpoint selection for 3D scene understanding. In Computer Graphics Forum, Vol. 35. 135--144.","journal-title":"Computer Graphics Forum"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00386"},{"key":"e_1_3_2_1_12_1","volume-title":"Adam: A method for stochastic optimization. (No Title)","author":"Diederik P Kingma","year":"2014","unstructured":"P Kingma Diederik. 2014. Adam: A method for stochastic optimization. (No Title) (2014)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"e_1_3_2_1_14_1","volume-title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels. In ACM SIGGRAPH Asia 2022 Conference Papers. 1--8.","author":"Fang Jiemin","year":"2022","unstructured":"Jiemin Fang, Taoran Yi, Xinggang Wang, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Matthias Nie, and Yong-Jin Kim. 2022. Fast Dynamic Radiance Fields with Time-Aware Neural Voxels. In ACM SIGGRAPH Asia 2022 Conference Papers. 1--8."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555383"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"e_1_3_2_1_19_1","volume-title":"Gaussianflow: Splatting gaussian dynamics for 4d content creation. arXiv preprint arXiv:2403.12365","author":"Gao Quankai","year":"2024","unstructured":"Quankai Gao, Qiangeng Xu, Zhe Cao, Ben Mildenhall, Wenchao Ma, Le Chen, Danhang Tang, and Ulrich Neumann. 2024. Gaussianflow: Splatting gaussian dynamics for 4d content creation. arXiv preprint arXiv:2403.12365 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01468"},{"key":"e_1_3_2_1_21_1","volume-title":"Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering. arXiv preprint arXiv:2312.00109","author":"Huang Tao","year":"2023","unstructured":"Tao Huang, Hao Gao, Zexin Zhang, Baining Guo, Yanlin Zhou, and Zhewei Zhang. 2023. Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering. arXiv preprint arXiv:2312.00109 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML). 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32nd International Conference on Machine Learning (ICML). 448--456."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_26_1","volume-title":"GHuNeRF: Generalizable Human NeRF from a Monocular Video. arXiv preprint arXiv:2308.16576","author":"Li Chen","year":"2023","unstructured":"Chen Li, Jihao Lin, and Gim Hee Lee. 2023. GHuNeRF: Generalizable Human NeRF from a Monocular Video. arXiv preprint arXiv:2308.16576 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657520"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"e_1_3_2_1_31_1","volume-title":"High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes. In SIGGRAPH Asia Conference Proceedings.","author":"Lin Haotong","year":"2023","unstructured":"Haotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei Zhou. 2023. High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes. In SIGGRAPH Asia Conference Proceedings."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01997"},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Learning Representations.","author":"Liu Yunzhu","year":"2019","unstructured":"Yunzhu Liu, Kevin Shao, Tao Langlois, Pitchaya Sen, Pulkit Agrawal, Noah Snavely, Doug Davis, Judith Bula Grossman, Kimberly Stachenfeld, and Leonidas J Guibas. 2019. Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00010"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Jonathon Luiten Georgios Kopanas Bastian Leibe and Deva Ramanan. 2024. Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis. In 3DV.","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"e_1_3_2_1_37_1","volume-title":"European Conference on Computer Vision. Springer, 313--332","author":"Mihajlovic Marko","year":"2024","unstructured":"Marko Mihajlovic, Sergey Prokudin, Siyu Tang, Robert Maier, Federica Bogo, Tony Tung, and Edmond Boyer. 2024. Splatfields: Neural gaussian splats for sparse 3d and 4d reconstruction. In European Conference on Computer Vision. Springer, 313--332."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"e_1_3_2_1_40_1","volume-title":"Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228","author":"Park Keunhong","year":"2021","unstructured":"Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, and Steven M Seitz. 2021. Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228 (2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"Convolutional Occupancy Networks. In European Conference on Computer Vision. 523--540","author":"Peng Songyou","year":"2020","unstructured":"Songyou Peng, Michael Niemeyer, Lars Mescheder, Marc Pollefeys, and Andreas Geiger. 2020. Convolutional Occupancy Networks. In European Conference on Computer Vision. 523--540."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_2_1_44_1","volume-title":"A mathematical theory of communication. The Bell system technical journal 27, 3","author":"Shannon Claude E","year":"1948","unstructured":"Claude E Shannon. 1948. A mathematical theory of communication. The Bell system technical journal 27, 3 (1948), 379--423."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01596"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing. 1056--1063","author":"Shi Shuran","year":"2021","unstructured":"Shuran Shi, Chuhang Wang, Gaoxiang Fang, and Sheng Wang. 2021. Selfsupervised learning of point clouds via orientation estimation. In Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing. 1056--1063."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247082"},{"key":"e_1_3_2_1_48_1","first-page":"7537","article-title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","volume":"33","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul P Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T Barron, and Ren Ng. 2020. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains. In Advances in Neural Information Processing Systems, Vol. 33. 7537--7547.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","volume-title":"Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv preprint arXiv:1607.08022","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2016. Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv preprint arXiv:1607.08022 (2016)."},{"volume-title":"International journal of computer vision","author":"Viola Paul","key":"e_1_3_2_1_50_1","unstructured":"Paul Viola and William M Wells III. 1997. Alignment by maximization of mutual information. In International journal of computer vision, Vol. 24. 137--154."},{"key":"e_1_3_2_1_51_1","volume-title":"Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction. arXiv preprint arXiv:2406.03697","author":"Wan Diwen","year":"2024","unstructured":"Diwen Wan, Ruijie Lu, and Gang Zeng. 2024. Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction. arXiv preprint arXiv:2406.03697 (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction. Advances in neural information processing systems","author":"Wang Feng","year":"2023","unstructured":"Feng Wang, Zilong Chen, Guokang Wang, Yafei Song, and Huaping Liu. 2023. Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction. Advances in neural information processing systems (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01805"},{"key":"e_1_3_2_1_54_1","volume-title":"andWenping Wang","author":"Liu Lingjie","year":"2021","unstructured":"PengWang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, andWenping Wang. 2021. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"e_1_3_2_1_56_1","volume-title":"The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers","volume":"2","author":"Simoncelli Eero P","year":"2003","unstructured":"ZhouWang, Eero P Simoncelli, and Alan C Bovik. 2003. Multiscale structural similarity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, Vol. 2. Ieee, 1398--1402."},{"key":"e_1_3_2_1_57_1","volume-title":"Multi-modal","author":"William M","year":"1996","unstructured":"William M Wells III, Paul Viola, Hideki Atsumi, Shin Nakajima, and Ron Kikinis. 1996. Multi-modal volume registration by maximization of mutual information. Medical image analysis 1, 1 (1996), 35--51."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"e_1_3_2_1_59_1","volume-title":"Group Normalization. In Proceedings of the European Conference on Computer Vision (ECCV). 3--19","author":"Wu Yuxin","year":"2018","unstructured":"Yuxin Wu and Kaiming He. 2018. Group Normalization. In Proceedings of the European Conference on Computer Vision (ECCV). 3--19."},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8856--8865","author":"Xie Yinyu","year":"2022","unstructured":"Yinyu Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, and Srinath Sridhar. 2022. Neural fields as learnable kernels for 3D reconstruction. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8856--8865."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00801"},{"key":"e_1_3_2_1_62_1","volume-title":"Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction. arXiv preprint arXiv:2309.13101","author":"Yang Ziyi","year":"2023","unstructured":"Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, and Xiaogang Jin. 2023. Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction. arXiv preprint arXiv:2309.13101 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting. arXiv preprint arXiv:2310.10642","author":"Yang Zeyu","year":"2023","unstructured":"Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, and Li Zhang. 2023. Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting. arXiv preprint arXiv:2310.10642 (2023)."},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 21302--21311","author":"Yenamandra Varun","year":"2023","unstructured":"Varun Yenamandra, Sai Gopal Kanaparthy, Akash Sridhar, Tejan Thawakar, Anant Ranade, and Shubham Duggal. 2023. NeRF-Breaker: Breaking NeRF Reconstruction Using Adversarial Attacks. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 21302--21311."},{"key":"e_1_3_2_1_65_1","volume-title":"Mip-Splatting: Alias-free 3D Gaussian Splatting. arXiv preprint arXiv:2311.16493","author":"Yu Zehao","year":"2023","unstructured":"Zehao Yu, Songyou Peng, Yiwen Liao, Jiaxiang Zhang, Matthias Nie\u00dfner, and Andreas Geiger. 2023. Mip-Splatting: Alias-free 3D Gaussian Splatting. arXiv preprint arXiv:2311.16493 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_67_1","volume-title":"Dynpoint: Dynamic neural point for view synthesis. Advances in Neural Information Processing Systems 36","author":"Zhou Kaichen","year":"2024","unstructured":"Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, and Niki Trigoni. 2024. Dynpoint: Dynamic neural point for view synthesis. Advances in Neural Information Processing Systems 36 (2024)."}],"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\/3746027.3755121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:59:15Z","timestamp":1765310355000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":67,"alternative-id":["10.1145\/3746027.3755121","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755121","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"}}]}}