{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T16:19:23Z","timestamp":1780071563700,"version":"3.54.0"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202142"],"award-info":[{"award-number":["62202142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key Scientific Research Projects of Higher Education Institutions","award":["24A520007"],"award-info":[{"award-number":["24A520007"]}]},{"name":"Guangxi Key Lab of Multi-source Information Mining and Security","award":["MIMS22-12"],"award-info":[{"award-number":["MIMS22-12"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>Point clouds play an essential role in 3D visual media applications. Point Cloud Quality Assessment (PCQA) is vital to improving the subjective experience, but lacking an effective geometric characterization hinders its consistency with subjective perception. To tackle this problem, this article introduces a No-Reference Multi-Modal Point Cloud Quality Assessment (NR-PCQA) approach driven by adaptive geometric attention. Specifically, this article defines two dimensionless geometric descriptors, namely Radial Depth Ratio (RDR) and Relative Radial Distance (RRD). These two descriptors are then used to construct an Adaptive Geometric Attention Mechanism (AGAM), which dynamically guides the network to focus on features related to geometric quality during feature extraction. Based on AGAM, a multi-modal fusion framework is further built, where the 3D geometric cues are combined with the texture and semantic information of the 2D projection images, leading to accurate PCQA. Creatively, the Hierarchical Multi-Modal Attention Fusion (HMAF) mechanism is designed to achieve the complementary strengths of 3D and 2D features, which first maximizes the extraction of single-modal features and then deeply merges cross-modal information. Naturally, the experimental results on SJTU-PCQA and WPC databases demonstrate that the innovative design of AGAM and HMAF achieves effective multi-modal feature fusion on the basis of satisfactory description for geometric properties, resulting in higher subjective consistency than the state-of-the-art methods. Meanwhile, the proposed method exhibits strong robustness across various types of point cloud distortions and diverse point cloud content, providing comprehensive validation of its effectiveness and practicality.<\/jats:p>","DOI":"10.1145\/3795690","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T14:21:33Z","timestamp":1770646893000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Geometric Attention-Driven No-Reference Multi-Modal Point Cloud Quality Assessment"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7413-2869","authenticated-orcid":false,"given":"Zhihao","family":"Jia","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1319-1266","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6788-3323","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8922-4806","authenticated-orcid":false,"given":"Yonghua","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3366-6155","authenticated-orcid":false,"given":"Yang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8603-4161","authenticated-orcid":false,"given":"Ziqing","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Henan University, Zhengzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2353-5318","authenticated-orcid":false,"given":"Shiguang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,3,7]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3023541"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2011.43"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3150522"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3549179"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-019-09320-4"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594299"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00915"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191308"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3436880"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2745941"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3036153"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130003"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3450728"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209388"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743313"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213831"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9106005"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123147"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3047083"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096060"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347638"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3264105"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664199"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455967"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3282802"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB53066.2021.9547070"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475645"},{"key":"e_1_3_2_29_2","first-page":"1","article-title":"Cmdc-pcqa: No-reference point cloud quality assessment via a cross-modal deep-coupling framework","author":"Wu Biqi","year":"2025","unstructured":"Biqi Wu, Xiwu Shang, Xiaoli Zhao, Liquan Shen, Ping An, and Siwei Ma. 2025. Cmdc-pcqa: No-reference point cloud quality assessment via a cross-modal deep-coupling framework. IEEE Transactions on Instrumentation and Measurement 74 (2025), 1\u201313.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_3_2_30_2","first-page":"129817","article-title":"Point cloud quality assessment using the perceptual clustering weighted graph (pcw-graph) and attention fusion network","author":"Laazoufi Abdelouahed","year":"2025","unstructured":"Abdelouahed Laazoufi, Mohammed El Hassouni, and Hocine Cherifi. 2025. Point cloud quality assessment using the perceptual clustering weighted graph (pcw-graph) and attention fusion network. Expert Systems with Applications 299 (2025), 129817.","journal-title":"Expert Systems with Applications"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3186894"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3550274"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3532651"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/195"},{"key":"e_1_3_2_35_2","first-page":"16332","article-title":"Evaluation criteria for point cloud compression","author":"Mekuria Rufael","year":"2016","unstructured":"Rufael Mekuria, Zhu Li, Christian Tulvan, and Phil Chou. Evaluation criteria for point cloud compression. ISO\/IEC MPEG (2016), 16332.","journal-title":"ISO\/IEC MPEG"},{"key":"e_1_3_2_36_2","first-page":"174","volume-title":"Proceedings of the Applications of Digital Image Processing XLI","author":"Torlig Eric M.","year":"2018","unstructured":"Eric M. Torlig, Evangelos Alexiou, Tiago A. Fonseca, Ricardo L. de Queiroz, and Touradj Ebrahimi. 2018. A novel methodology for quality assessment of voxelized point clouds. In Proceedings of the Applications of Digital Image Processing XLI. SPIE, 174\u2013190."},{"key":"e_1_3_2_37_2","volume-title":"Point Cloud Distortion Quantification Based on Potential Energy for Human and Machine Perception","author":"Yang Qi","year":"2021","unstructured":"Qi Yang. 2021. Point Cloud Distortion Quantification Based on Potential Energy for Human and Machine Perception. eScholarship, University of California."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100282"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02050"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445736"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3423830"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102450"},{"key":"e_1_3_2_43_2","first-page":"652","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi Charles R.","year":"2017","unstructured":"Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652\u2013660."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2952707"},{"key":"e_1_3_2_47_2","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume":"34","author":"Huang Yu","year":"2021","unstructured":"Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, and Longbo Huang. 2021. What makes multi-modal learning better than single (provably). Advances in Neural Information Processing Systems 34 (2021), 10944\u201310956.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3033117"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103449"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611998"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410052"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3350180"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122953"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"},{"key":"e_1_3_2_55_2","first-page":"5099","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Ruizhongtai Qi Charles","year":"2017","unstructured":"Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems 30 (2017), 5099\u20135108.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_56_2","first-page":"23192","article-title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies","volume":"35","author":"Qian Guocheng","year":"2022","unstructured":"Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Hammoud, Mohamed Elhoseiny, and Bernard Ghanem. 2022. Pointnext: Revisiting pointnet++ with improved training and scaling strategies. Advances in Neural Information Processing Systems 35 (2022), 23192\u201323204.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_57_2","unstructured":"Qian-Yi Zhou Jaesik Park and Vladlen Koltun. 2018. Open3d: A modern library for 3d data processing. arXiv:1801.09847. Retrieved from https:\/\/arxiv.org\/abs\/1801.09847"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3167151"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101484"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296925"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3582309"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3024065"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643817"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521845"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102882"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-025-01887-2"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795690","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:24:42Z","timestamp":1773494682000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795690"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,7]]},"references-count":67,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3795690"],"URL":"https:\/\/doi.org\/10.1145\/3795690","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,7]]},"assertion":[{"value":"2025-07-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}