{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:04:24Z","timestamp":1765339464665,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"name":"Shandong Provincial Natural Science Foundation","award":["ZR2024QF215"],"award-info":[{"award-number":["ZR2024QF215"]}]},{"name":"Key Research and Development Program of Rizhao","award":["2024ZDYF010053"],"award-info":[{"award-number":["2024ZDYF010053"]}]},{"name":"National Natural Science Foundation","award":["62072020"],"award-info":[{"award-number":["62072020"]}]},{"name":"Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University","award":["VRLAB2024A**"],"award-info":[{"award-number":["VRLAB2024A**"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755361","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"4222-4231","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Localization using Hybrid Feature Grid and Learned Weighted Global Point Cloud"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3191-1662","authenticated-orcid":false,"given":"Junyi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, Shandong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9304-1933","authenticated-orcid":false,"given":"Yue","family":"Qi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China and Qingdao Research Institute of Beihang University, Qingdao, Shandong, 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\/LRA.2021.3068640"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2860039"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00489"},{"key":"e_1_3_2_1_5_1","first-page":"778","volume-title":"Heraklion","author":"Calonder Michael","year":"2010","unstructured":"Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. 2010. Brief: Binary robust independent elementary features. In Computer Vision-ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV 11. 778-792."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3075644"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01983"},{"key":"e_1_3_2_1_8_1","volume-title":"Map-Relative Pose Regression for Visual Re-Localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20665-20674","author":"Chen Shuai","year":"2024","unstructured":"Shuai Chen, Tommaso Cavallari, Victor Adrian Prisacariu, and Eric Brachmann. 2024b. Map-Relative Pose Regression for Visual Re-Localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20665-20674."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_1"},{"key":"e_1_3_2_1_10_1","volume-title":"Learning To Detect Scene Landmarks for Camera Localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11132-11142","author":"Do Tien","year":"2022","unstructured":"Tien Do, Ondrej Miksik, Joseph DeGol, Hyun Soo Park, and Sudipta N Sinha. 2022. Learning To Detect Scene Landmarks for Camera Localization. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11132-11142."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Ron Ferens and Yosi Keller. 2025. HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset.","DOI":"10.1109\/CVPR52734.2025.01078"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00555"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01841"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_15_1","volume-title":"From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting. arXiv preprint arXiv:2503.19358","author":"Huang Zhiwei","year":"2025","unstructured":"Zhiwei Huang, Hailin Yu, Yichun Shentu, Jin Yuan, and Guofeng Zhang. 2025. From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting. arXiv preprint arXiv:2503.19358 (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.694"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.113"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681628"},{"key":"e_1_3_2_1_23_1","volume-title":"Learning Neural Volumetric Pose Features for Camera Localization. In European Conference on Computer Vision. Springer, 198-214","author":"Lin Jingyu","year":"2024","unstructured":"Jingyu Lin, Jiaqi Gu, Bojian Wu, Lubin Fan, Renjie Chen, Ligang Liu, and Jieping Ye. 2024a. Learning Neural Volumetric Pose Features for Camera Localization. In European Conference on Computer Vision. Springer, 198-214."},{"key":"e_1_3_2_1_24_1","volume-title":"Robust Data Association Against Detection Deficiency for Semantic SLAM","author":"Lin Xubin","year":"2023","unstructured":"Xubin Lin, Jiahao Ruan, Yirui Yang, Li He, Yisheng Guan, and Hong Zhang. 2023. Robust Data Association Against Detection Deficiency for Semantic SLAM. IEEE Transactions on Automation Science and Engineering (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Learning Representations.","author":"Liu Changkun","year":"2025","unstructured":"Changkun Liu, Shuai Chen, Yash Sanjay Bhalgat, Siyan Hu, Ming Cheng, Zirui Wang, Victor Adrian Prisacariu, and Tristan Braud. 2025. GS-CPR: Efficient camera pose refinement via 3D gaussian splatting. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.260"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01708"},{"volume-title":"Computer Graphics Forum","author":"Mellado Nicolas","key":"e_1_3_2_1_28_1","unstructured":"Nicolas Mellado, Dror Aiger, and Niloy J Mitra. 2014. Super 4pcs fast global pointcloud registration via smart indexing. In Computer Graphics Forum, , Vol. 33. Wiley Online Library, 205-215."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00030"},{"key":"e_1_3_2_1_31_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.377"},{"key":"e_1_3_2_1_35_1","volume-title":"icomma: Inverting 3d gaussians splatting for camera pose estimation via comparing and matching. arXiv preprint arXiv:2312.09031","author":"Sun Yuan","year":"2023","unstructured":"Yuan Sun, Xuan Wang, Yunfan Zhang, Jie Zhang, Caigui Jiang, Yu Guo, and Fei Wang. 2023. icomma: Inverting 3d gaussians splatting for camera pose estimation via comparing and matching. arXiv preprint arXiv:2312.09031 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00187"},{"key":"e_1_3_2_1_37_1","volume-title":"TopNet: Structural Point Cloud Decoder. In IEEE Conference on Computer Vision and Pattern Recognition. 383-392","author":"Tchapmi Lyne P","year":"2019","unstructured":"Lyne P Tchapmi, Vineet Kosaraju, Hamid Rezatofighi, Ian Reid, and Silvio Savarese. 2019. TopNet: Structural Point Cloud Decoder. In IEEE Conference on Computer Vision and Pattern Recognition. 383-392."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01215"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"e_1_3_2_1_40_1","volume-title":"GLACE: Global Local Accelerated Coordinate Encoding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 21562-21571","author":"Wang Fangjinhua","year":"2024","unstructured":"Fangjinhua Wang, Xudong Jiang, Silvano Galliani, Christoph Vogel, and Marc Pollefeys. 2024a. GLACE: Global Local Accelerated Coordinate Encoding. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 21562-21571."},{"key":"e_1_3_2_1_41_1","volume-title":"IEEE International Conference on Robotics and Automation. 5891-5897","author":"Wang Junyi","year":"2021","unstructured":"Junyi Wang and Yue Qi. 2021. Camera relocalization using deep point cloud generation and hand-crafted feature refinement. In IEEE International Conference on Robotics and Automation. 5891-5897."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR59233.2023.00022"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR55154.2023.00041"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109914"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2023.100187"},{"key":"e_1_3_2_1_46_1","volume-title":"Look at the Sky: Sky-aware Efficient 3D Gaussian Splatting in the Wild","author":"Wang Yuze","year":"2025","unstructured":"Yuze Wang, Junyi Wang, Ruicheng Gao, Yansong Qu, Wantong Duan, Shuo Yang, and Yue Qi. 2025. Look at the Sky: Sky-aware Efficient 3D Gaussian Splatting in the Wild. IEEE Transactions on Visualization and Computer Graphics (2025)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681431"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2021.100045"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01853"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00013"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2909168"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109023"},{"key":"e_1_3_2_1_54_1","volume-title":"Gaussian-slam: Photo-realistic dense slam with gaussian splatting. arXiv preprint arXiv:2312.10070","author":"Yugay Vladimir","year":"2023","unstructured":"Vladimir Yugay, Yue Li, Theo Gevers, and Martin R Oswald. 2023. Gaussian-slam: Photo-realistic dense slam with gaussian splatting. arXiv preprint arXiv:2312.10070 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00497"},{"key":"e_1_3_2_1_56_1","volume-title":"European Conference on Computer Vision. Springer, 108-127","author":"Zhou Qunjie","year":"2024","unstructured":"Qunjie Zhou, Maxim Maximov, Or Litany, and Laura Leal-Taix\u00e9. 2024a. The nerfect match: Exploring nerf features for visual localization. In European Conference on Computer Vision. Springer, 108-127."},{"key":"e_1_3_2_1_57_1","volume-title":"European Conference on Computer Vision. 108-127","author":"Zhou Qunjie","year":"2024","unstructured":"Qunjie Zhou, Maxim Maximov, Or Litany, and Laura Leal-Taix\u00e9. 2024b. The nerfect match: Exploring nerf features for visual localization. In European Conference on Computer Vision. 108-127."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3483032"}],"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\/3746027.3755361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:59:58Z","timestamp":1765339198000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755361"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":58,"alternative-id":["10.1145\/3746027.3755361","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755361","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"}}]}}