{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T15:43:23Z","timestamp":1786722203849,"version":"build-2736575974"},"reference-count":70,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"RGC General Research Fund","award":["11200323"],"award-info":[{"award-number":["11200323"]}]},{"name":"NSFC\/RGC JRS Project","award":["N_CityU198\/24"],"award-info":[{"award-number":["N_CityU198\/24"]}]},{"DOI":"10.13039\/501100007156","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"crossref","award":["GHP\/044\/21SZ and PRP\/036\/24FX."],"award-info":[{"award-number":["GHP\/044\/21SZ and PRP\/036\/24FX."]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"crossref"}]}],"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>\n                    Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this article, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to tailor for point cloud lossless attribute compression. We develop a point-wise attention model using a permutation-invariant Transformer to tackle the challenges of sparsity and irregularity of point clouds during context modeling. We also propose a Density-Adaptive Learning Descriptor (DALD) capable of capturing structure and correlations among points across a large range of neighbors. In addition, we develop a prior-guided block partitioning to reduce the attribute variance within blocks and enhance the performance. Experiments on LiDAR and object point clouds show that DALD-PCAC achieves the state-of-the-art performance on most data. Our method boosts the compression performance and is robust to the varying densities of point clouds. Moreover, it guarantees a good tradeoff between performance and complexity, exhibiting great potential in real-world applications. The source code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/zb12138\/DALD_PCAC\">https:\/\/github.com\/zb12138\/DALD_PCAC<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3785465","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T14:21:33Z","timestamp":1770646893000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1487-9533","authenticated-orcid":false,"given":"Chunyang","family":"Fu","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-3968","authenticated-orcid":false,"given":"Ge","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7429-5495","authenticated-orcid":false,"given":"Wei","family":"Gao","sequence":"additional","affiliation":[{"name":"Peking University Shenzhen Graduate School, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3583-959X","authenticated-orcid":false,"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8246-177X","authenticated-orcid":false,"given":"Zhu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Missouri-Kansas City, Kansas City, Missouri, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1442-1207","authenticated-orcid":false,"given":"Shan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Palo Alto, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"22170","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Biswas Sourav","year":"2020","unstructured":"Sourav Biswas, Jerry Liu, Kelvin Wong, Shenlong Wang, and Raquel Urtasun. 2020. MuSCLE: Multi sweep compression of LiDAR using deep entropy models. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS), Vol. 33, 22170\u201322181."},{"key":"e_1_3_2_3_2","author":"MPEG 3D","year":"2016","unstructured":"MPEG 3D Graphics Group. 2016. Use Cases for Point Cloud Compression (PCC). Technical Report N16331, ISO\/IEC JTC1\/SC29\/WG11 MPEG.","journal-title":"Use Cases for Point Cloud Compression (PCC)"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2022.846972"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2020.12"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2018.2885981"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2575005"},{"key":"e_1_3_2_8_2","unstructured":"MPEG 3D Graphics Group. 2021. G-PCC Codec Description. Technical Report W20626 ISO\/IEC JTC1\/SC29\/WG11 MPEG."},{"key":"e_1_3_2_9_2","unstructured":"Wei Yan Shan Liu Thomas H. Li Zhu Li and Ge Li. 2019. Deep autoencoder-based lossy geometry compression for point clouds. arXiv:1905.03691. Retrieved from https:\/\/arxiv.org\/abs\/1905.03691"},{"key":"e_1_3_2_10_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_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100279"},{"issue":"2","key":"e_1_3_2_12_2","first-page":"1687","article-title":"Sparse tensor-based multiscale representation for point cloud geometry compression","volume":"45","author":"Wang Jianqiang","year":"2022","unstructured":"Jianqiang Wang, Dandan Ding, Zhu Li, Xiaoxing Feng, Chuntong Cao, and Zhan Ma. 2022. Sparse tensor-based multiscale representation for point cloud geometry compression. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 2 (2022), 1687\u20131701.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3047520"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19942"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01381"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00343"},{"key":"e_1_3_2_17_2","unstructured":"Andr\u00e9 F. R. Guarda Nuno M. M. Rodrigues and Fernando Pereira. 2024. The jpeg pleno learning-based point cloud coding standard: Serving man and machine. arXiv:2409.08130. Retrieved from https:\/\/arxiv.org\/abs\/2409.08130"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086711"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01440"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239321"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/DCC55655.2023.00031"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455990"},{"issue":"10","key":"e_1_3_2_23_2","first-page":"5637","article-title":"Block-adaptive point cloud attribute coding with region-aware optimized transform","volume":"33","author":"Song Fei","year":"2023","unstructured":"Fei Song, Ge Li, Xiaodong Yang, Wei Gao, and Shan Liu. 2023. Block-adaptive point cloud attribute coding with region-aware optimized transform. IEEE Transactions on Circuits and Systems for Video Technology 33, 10 (2023), 5637\u20135650.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25121"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096990"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3059633"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00237"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095458"},{"key":"e_1_3_2_29_2","unstructured":"Jeff Ford and Jordan Ford. 2022. Lossless SIMD compression of LiDAR range and attribute scan sequences. arXiv:2209.08196. Retrieved from https:\/\/arxiv.org\/abs\/2209.08196"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01670"},{"key":"e_1_3_2_31_2","unstructured":"Yiqi Jin Ziyu Zu Tongda Xu Yuhuan Lin and Yan Wang. 2022. ECM-OPCC: Efficient context model for octree-based point cloud compression. arXiv:2211.10916. Retrieved from https:\/\/arxiv.org\/abs\/2211.10916"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462684"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.70441"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936738"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532583"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305131"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3015901"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2699922"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446200"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.1109\/TMM.2024.3521845","article-title":"No-reference point cloud quality assessment via graph convolutional network","volume":"27","author":"Chen Wu","year":"2024","unstructured":"Wu Chen, Qiuping Jiang, Wei Zhou, Feng Shao, Guangtao Zhai, and Weisi Lin. 2024. No-reference point cloud quality assessment via graph convolutional network. IEEE Transactions on Multimedia 27 (2024), 2489\u20132502.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2908095"},{"key":"e_1_3_2_45_2","unstructured":"Mpeg. 2022. TMC13 Reference Software. Retrieved May 02 2022 from https:\/\/github.com\/MPEGGroup\/mpeG-PCC-tmc13"},{"key":"e_1_3_2_46_2","unstructured":"Khaled Mammou Alexis Tourapis Jungsun Kim Fabrice Robinet Valery Valentin and Yeping Su. 2018. Proposal for Improved Lossy Compression in TMC1. Technical Report M42640 ISO\/IEC JTC1\/SC29\/WG11 MPEG."},{"key":"e_1_3_2_47_2","author":"MPEG 3D","year":"2017","unstructured":"MPEG 3D Graphics Group. 2017. PCC Test Model Category 3 v0. Technical Report N17249, ISO\/IEC JTC1\/SC29\/WG11 MPEG.","journal-title":"PCC Test Model Category 3 v0"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3186532"},{"key":"e_1_3_2_49_2","first-page":"1","volume-title":"Proceedings of the IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","author":"Yin Qian","year":"2021","unstructured":"Qian Yin, Qingshan Ren, Lili Zhao, Wenyi Wang, and Jianwen Chen. 2021. Lossless point cloud attribute compression with normal-based intra prediction. In Proceedings of the IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), 1\u20135."},{"key":"e_1_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Yan Huang Bin Wang C.-C. Jay Kuo Hui Yuan and Jingliang Peng. 2021. Hierarchical bit-wise differential coding (HBDC) of point cloud attributes. In Proceedings of the 2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP \u201921) 4215\u20134219.","DOI":"10.1109\/ICASSP39728.2021.9413427"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2543039"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3016894"},{"key":"e_1_3_2_53_2","first-page":"3309","volume-title":"Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP)","author":"Quach Maurice","year":"2020","unstructured":"Maurice Quach, Giuseppe Valenzise, and Frederic Dufaux. 2020. Folding-based compression of point cloud attributes. In Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), 3309\u20133313."},{"key":"e_1_3_2_54_2","first-page":"18","volume-title":"Proceedings of the Applications of Digital Image Processing XLIII","volume":"11510","author":"Alexiou Evangelos","year":"2020","unstructured":"Evangelos Alexiou, Kuan Tung, and Touradj Ebrahimi. 2020. Towards neural network approaches for point cloud compression. In Proceedings of the Applications of Digital Image Processing XLIII, Vol. 11510, 18\u201337."},{"key":"e_1_3_2_55_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201923)","author":"Pinheiro Rodrigo B.","year":"2023","unstructured":"Rodrigo B. Pinheiro, Jean-Eudes Marvie, Giuseppe Valenzise, Fr\u00e9d\u00e9ric, and Dufaux, N. F. 2023. PCAC: Normalizing flow based point cloud attribute compression. In Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201923), 1\u20135."},{"key":"e_1_3_2_56_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP \u201923)","author":"Nguyen Dat Thanh","year":"2023","unstructured":"Dat Thanh Nguyen, Kamal Gopikrishnan Nambiar, and Andr\u00e9 Kaup. 2023. Deep probabilistic model for lossless scalable point cloud attribute compression. In Proceedings of the 2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP \u201923), 1\u20135."},{"key":"e_1_3_2_57_2","unstructured":"MPEG 3D Graphics and Haptics Coding. 2022. Common Test Conditions for G-PCC. Technical Report N0427 ISO\/IEC JTC 1\/SC 29\/WG 7 MPEG."},{"key":"e_1_3_2_58_2","unstructured":"D. Flynn and K. Mammou. 2021. G-PCC: Changes to CTC. Input Document m57468 ISO\/IEC JTC1\/SC29\/WG11 MPEG."},{"key":"e_1_3_2_59_2","unstructured":"MPEG 3D Graphics Group. 2020. Report on Modifying Entropy Coding of Attributes Coefficients with Dictionary Removal and Run-Length Coding. Technical Report m54265 ISO\/IEC JTC1\/SC29\/WG11 MPEG."},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000004"},{"key":"e_1_3_2_61_2","volume-title":"Elements of Information Theory","author":"Cover Thomas M.","year":"2006","unstructured":"Thomas M. Cover and Joy A. Thomas. 2006. Elements of Information Theory (2nd ed.). John Wiley & Sons."},{"key":"e_1_3_2_62_2","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. In Proceedings of the Advances in Neural Information Processing Systems Vol. 30."},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"e_1_3_2_64_2","unstructured":"Henrique Malvar and Gary Sullivan. 2003. YCoCg-R: A color space with RGB reversibility and low dynamic range. ISO\/IEC JTC1\/SC29\/WG11 and ITU-T SG16 Q 6."},{"key":"e_1_3_2_65_2","unstructured":"Charles Loop Qin Cai Sergio Orts Escolano and Philip A. Chou. 2016. Microsoft voxelized upper bodies\u2014A voxelized point cloud dataset. Input Document m38673\/M72012 ISO\/IEC JTC1\/SC29 Joint WG11\/WG1 (MPEG\/JPEG) Geneva."},{"key":"e_1_3_2_66_2","unstructured":"Eugene d\u2019Eon Bob Harrison Taos Myers and Philip A. Chou. 2017. 8i voxelized full bodies version 2\u2014A voxelized point cloud dataset. Input Document m40059\/M74006 ISO\/IEC JTC1\/SC29 Joint WG11\/WG1 (MPEG\/JPEG) Geneva."},{"key":"e_1_3_2_67_2","unstructured":"Yi Xu Yao Lu and Ziyu Wen. 2017. Owlii Dynamic human mesh sequence dataset. Input document m41658 ISO\/IEC JTC1\/SC29\/WG11 MPEGMacau."},{"key":"e_1_3_2_68_2","unstructured":"Dingquan Li Jing Wang and Ge Li. 2022. A High-Quality Colored Point Cloud Dataset. Retrieved December 2024 from https:\/\/github.com\/lidq92\/PCD-PCL"},{"key":"e_1_3_2_69_2","unstructured":"MPEG 3D Graphics Group. 2022. Preliminary Dataset Collection for AI-Based Point Cloud Experiments. Technical report N00326 ISO\/IEC JTC1\/SC29\/WG11 MPEG."},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911400640"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3785465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T15:51:42Z","timestamp":1774281102000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785465"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":70,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3785465"],"URL":"https:\/\/doi.org\/10.1145\/3785465","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]},"assertion":[{"value":"2024-05-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}