{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T12:44:09Z","timestamp":1763729049297,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733406","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1710-1719","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6121-3990","authenticated-orcid":false,"given":"Jingrui","family":"Ye","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6515-0814","authenticated-orcid":false,"given":"Zhongkai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7509-3964","authenticated-orcid":false,"given":"Qingmin","family":"Liao","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong, China"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_42"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01978"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_14"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01139"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01595"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00846"},{"volume-title":"Point-based graphics","author":"Gross Markus","key":"e_1_3_2_1_10_1","unstructured":"Markus Gross and Hanspeter Pfister. 2011. Point-based graphics. Elsevier."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. arXiv preprint arXiv:2312.02134","author":"Hu Liangxiao","year":"2023","unstructured":"Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, and Liqiang Nie. 2023. Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. arXiv preprint arXiv:2312.02134 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"SHERF: Generalizable Human NeRF from a Single Image. arXiv preprint arXiv:2303.12791","author":"Hu Shoukang","year":"2023","unstructured":"Shoukang Hu, Fangzhou Hong, Liang Pan, Haiyi Mei, Lei Yang, and Ziwei Liu. 2023. SHERF: Generalizable Human NeRF from a Single Image. arXiv preprint arXiv:2303.12791 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Gauhuman: Articulated gaussian splatting from monocular human videos. arXiv preprint arXiv:2312.02973","author":"Hu Shoukang","year":"2023","unstructured":"Shoukang Hu and Ziwei Liu. 2023. Gauhuman: Articulated gaussian splatting from monocular human videos. arXiv preprint arXiv:2312.02973 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior. arXiv preprint arXiv:2207.05375","author":"Huang Buzhen","year":"2022","unstructured":"Buzhen Huang, Yuan Shu, Jingyi Ju, and Yangang Wang. 2022. Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior. arXiv preprint arXiv:2207.05375 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01623"},{"key":"e_1_3_2_1_18_1","volume-title":"Hifi4g: High-fidelity human performance rendering via compact gaussian splatting. arXiv preprint arXiv:2312.03461","author":"Jiang Yuheng","year":"2023","unstructured":"Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, and Lan Xu. 2023. Hifi4g: High-fidelity human performance rendering via compact gaussian splatting. arXiv preprint arXiv:2312.03461 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"e_1_3_2_1_20_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_21_1","volume-title":"James Gabriel, Oncel Tuzel, and Anurag Ranjan.","author":"Kocabas Muhammed","year":"2023","unstructured":"Muhammed Kocabas, Jen-Hao Rick Chang, James Gabriel, Oncel Tuzel, and Anurag Ranjan. 2023. Hugs: Human gaussian splats. arXiv preprint arXiv:2311.17910 (2023)."},{"key":"e_1_3_2_1_22_1","first-page":"24741","article-title":"Neural human performer: Learning generalizable radiance fields for human performance rendering","volume":"34","author":"Kwon Youngjoong","year":"2021","unstructured":"Youngjoong Kwon, Dahun Kim, Duygu Ceylan, and Henry Fuchs. 2021. Neural human performer: Learning generalizable radiance fields for human performance rendering. Advances in Neural Information Processing Systems 34 (2021), 24741--24752.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"Gart: Gaussian articulated template models. arXiv preprint arXiv:2311.16099","author":"Lei Jiahui","year":"2023","unstructured":"Jiahui Lei, Yufu Wang, Georgios Pavlakos, Lingjie Liu, and Kostas Daniilidis. 2023. Gart: Gaussian articulated template models. arXiv preprint arXiv:2311.16099 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Human101: Training 100 fps human gaussians in 100s from 1 view. arXiv preprint arXiv:2312.15258","author":"Li Mingwei","year":"2023","unstructured":"Mingwei Li, Jiachen Tao, Zongxin Yang, and Yi Yang. 2023. Human101: Training 100 fps human gaussians in 100s from 1 view. arXiv preprint arXiv:2312.15258 (2023)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_26_1","volume-title":"Animatable gaussians: Learning pose-dependent gaussian maps for high-fidelity human avatar modeling. arXiv preprint arXiv:2311.16096","author":"Li Zhe","year":"2023","unstructured":"Zhe Li, Zerong Zheng, Lizhen Wang, and Yebin Liu. 2023. Animatable gaussians: Learning pose-dependent gaussian maps for high-fidelity human avatar modeling. arXiv preprint arXiv:2311.16096 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612368"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_3_2_1_29_1","volume-title":"Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713","author":"Luiten Jonathon","year":"2023","unstructured":"Jonathon Luiten, Georgios Kopanas, Bastian Leibe, and Deva Ramanan. 2023. Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_11"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_32_1","volume-title":"Human gaussian splatting: Real-time rendering of animatable avatars. arXiv preprint arXiv:2311.17113","author":"Moreau Arthur","year":"2023","unstructured":"Arthur Moreau, Jifei Song, Helisa Dhamo, Richard Shaw, Yiren Zhou, and Eduardo P\u00e9rez-Pellitero. 2023. Human gaussian splatting: Real-time rendering of animatable avatars. arXiv preprint arXiv:2311.17113 (2023)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00328"},{"key":"e_1_3_2_1_35_1","volume-title":"Ash: Animatable gaussian splats for efficient and photoreal human rendering. arXiv preprint arXiv:2312.05941","author":"Pang Haokai","year":"2023","unstructured":"Haokai Pang, Heming Zhu, Adam Kortylewski, Christian Theobalt, and Marc Habermann. 2023. Ash: Animatable gaussian splats for efficient and photoreal human rendering. arXiv preprint arXiv:2312.05941 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01405"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"e_1_3_2_1_39_1","volume-title":"Gaussianavatars: Photorealistic head avatars with rigged 3d gaussians. arXiv preprint arXiv:2312.02069","author":"Qian Shenhan","year":"2023","unstructured":"Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, and Matthias Nie\u00dfner. 2023. Gaussianavatars: Photorealistic head avatars with rigged 3d gaussians. arXiv preprint arXiv:2312.02069 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"3dgs-avatar: Animatable avatars via deformable 3d gaussian splatting. arXiv preprint arXiv:2312.09228","author":"Qian Zhiyin","year":"2023","unstructured":"Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, and Siyu Tang. 2023. 3dgs-avatar: Animatable avatars via deformable 3d gaussian splatting. arXiv preprint arXiv:2312.09228 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Embodied hands: Modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610","author":"Romero Javier","year":"2022","unstructured":"Javier Romero, Dimitrios Tzionas, and Michael J Black. 2022. Embodied hands: Modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530122"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547971"},{"key":"e_1_3_2_1_45_1","volume-title":"NPC: Neural Point Characters from Video. arXiv preprint arXiv:2304.02013","author":"Su Shih-Yang","year":"2023","unstructured":"Shih-Yang Su, Timur Bagautdinov, and Helge Rhodin. 2023. NPC: Neural Point Characters from Video. arXiv preprint arXiv:2304.02013 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475442"},{"key":"e_1_3_2_1_47_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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 30 (2017)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612236"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475412"},{"key":"e_1_3_2_1_50_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00058"},{"key":"e_1_3_2_1_53_1","volume-title":"4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528","author":"Wu Guanjun","year":"2023","unstructured":"Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, and XinggangWang. 2023. 4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Wild2Avatar: Rendering Humans Behind Occlusions. arXiv preprint arXiv:2401.00431","author":"Xiang Tiange","year":"2023","unstructured":"Tiange Xiang, Adam Sun, Scott Delp, Kazuki Kozuka, Li Fei-Fei, and Ehsan Adeli. 2023. Wild2Avatar: Rendering Humans Behind Occlusions. arXiv preprint arXiv:2401.00431 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00300"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"e_1_3_2_1_58_1","volume-title":"Gaussian head avatar: Ultra high-fidelity head avatar via dynamic gaussians. arXiv preprint arXiv:2312.03029","author":"Xu Yuelang","year":"2023","unstructured":"Yuelang Xu, Benwang Chen, Zhe Li, Hongwen Zhang, Lizhen Wang, Zerong Zheng, and Yebin Liu. 2023. Gaussian head avatar: Ultra high-fidelity head avatar via dynamic gaussians. arXiv preprint arXiv:2312.03029 (2023)."},{"key":"e_1_3_2_1_59_1","volume-title":"LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar. arXiv preprint arXiv:2305.01190","author":"Xu Yuelang","year":"2023","unstructured":"Yuelang Xu, Hongwen Zhang, LizhenWang, Xiaochen Zhao, Han Huang, Guojun Qi, and Yebin Liu. 2023. LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar. arXiv preprint arXiv:2305.01190 (2023)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3149229"},{"key":"e_1_3_2_1_61_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_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01308"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356513"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16943--16953","author":"Yu Zhengming","year":"2023","unstructured":"Zhengming Yu, Wei Cheng, Xian Liu,WayneWu, and Kwan-Yee Lin. 2023. Mono-Human: Animatable Human Neural Field from Monocular Video. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 16943--16953."},{"key":"e_1_3_2_1_65_1","volume-title":"Koki Nagano, Jan Kautz, and Umar Iqbal.","author":"Yuan Ye","year":"2023","unstructured":"Ye Yuan, Xueting Li, Yangyi Huang, Shalini De Mello, Koki Nagano, Jan Kautz, and Umar Iqbal. 2023. Gavatar: Animatable 3d gaussian avatars with implicit mesh learning. arXiv preprint arXiv:2312.11461 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548148"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548078"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_69_1","volume-title":"Gps-gaussian: Generalizable pixel-wise 3d gaussian splatting for real-time human novel view synthesis. arXiv preprint arXiv:2312.02155","author":"Zheng Shunyuan","year":"2023","unstructured":"Shunyuan Zheng, Boyao Zhou, Ruizhi Shao, Boning Liu, Shengping Zhang, Liqiang Nie, and Yebin Liu. 2023. Gps-gaussian: Generalizable pixel-wise 3d gaussian splatting for real-time human novel view synthesis. arXiv preprint arXiv:2312.02155 (2023)."},{"key":"e_1_3_2_1_70_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13545--13555","author":"Zheng Yufeng","year":"2022","unstructured":"Yufeng Zheng, Victoria Fern\u00e1ndez Abrevaya, Marcel C B\u00fchler, Xu Chen, Michael J Black, and Otmar Hilliges. 2022. Im avatar: Implicit morphable head avatars from videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13545--13555."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02017"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00369"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:11:22Z","timestamp":1755749482000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":72,"alternative-id":["10.1145\/3731715.3733406","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733406","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}