{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:29:22Z","timestamp":1785403762521,"version":"3.56.0"},"reference-count":25,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation","award":["2020-0-00011"],"award-info":[{"award-number":["2020-0-00011"]}]},{"award":["2020-0-00011"],"award-info":[{"award-number":["2020-0-00011"]}],"id":[{"id":"https:\/\/ror.org\/01g0hqq23","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00356924"],"award-info":[{"award-number":["RS-2024-00356924"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"award":["RS-2024-00356924"],"award-info":[{"award-number":["RS-2024-00356924"]}],"id":[{"id":"https:\/\/ror.org\/013aysd81","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>3D Gaussian Splatting (3DGS) has recently emerged as an effective representation for immersive 3D scene rendering, providing high visual fidelity and real-time rendering efficiency. To support interoperable compression of trained 3DGS content, the Moving Picture Experts Group (MPEG) is exploring Gaussian Splat Coding (GSC), which mainly targets already trained 3DGS models following the INRIA reference format. The current video-based GSC anchor reorders 3DGS attributes into 2D attribute maps using Parallel Assignment Linear Sorting (PLAS) and compresses the resulting maps using High Efficiency Video Coding (HEVC). However, higher-order spherical harmonic coefficients (SH-AC) often remain irregular and exhibit low local spatial correlation even after PLAS reordering, limiting the coding efficiency of conventional video codecs. This paper proposes a VQ-HEVC hybrid compression framework that is structurally compatible with the video-based GSC anchor framework, in which SH-AC coefficients are represented by vector quantization (VQ) indices, while the remaining attributes are encoded using the same HEVC-based procedure as the GSC anchor. The proposed method adopts a two-stage VQ scheme that combines coarse VQ and product-quantization-based residual quantization, together with zero-masked residual VQ and flexible PQ grouping, to improve index-map coding efficiency across rate points. The generated VQ indices are packed into YUV400 index-map sequences and encoded using HEVC lossless coding, while the corresponding codebooks are transmitted as metadata. Experimental results on the Bartender and Cinema sequences of the MPEG GSC CTC demonstrate consistent rate\u2013distortion improvements over the video-based GSC anchor across multiple objective quality metrics within the evaluated setting. In terms of RGB-PSNR, the proposed method achieves BD-rate reductions of 22.3% and 18.5% for the Bartender and Cinema datasets, respectively. These results suggest that, for the evaluated GSC CTC sequences, VQ-based SH-AC representation can effectively complement PLAS-based video coding while maintaining consistency with the existing GSC coding structure.<\/jats:p>","DOI":"10.3390\/s26134125","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:50:37Z","timestamp":1782867037000},"page":"4125","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Compression Method for Trained 3D Gaussian Splatting Models Based on VQ and HEVC"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9918-571X","authenticated-orcid":false,"given":"Dong-Ha","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Smart Air Mobility, Korea Aerospace University, Goyang 10540, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung-Yoon","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Smart Air Mobility, Korea Aerospace University, Goyang 10540, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwan-Jung","family":"Oh","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gwangsoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3686-4786","authenticated-orcid":false,"given":"Jae-Gon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Smart Air Mobility, Korea Aerospace University, Goyang 10540, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Rossi, S., Viola, I., Toni, L., and Cesar, P. (2023, January 7\u201310). Extending 3 DoF metrics to model user behaviour similarity in 6 DoF immersive applications. Proceedings of the 14th ACM Multimedia Systems Conference (MMSys), Vancouver, BC, Canada.","DOI":"10.1145\/3587819.3590976"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Tang, Z., Feng, C., Cheng, X., Yu, W., Zhang, J., Liu, Y., Long, X., Wang, W., and Yuan, L. (2025). NeuralGS: Bridging neural fields and 3D Gaussian splatting for compact 3D representations. arXiv.","DOI":"10.1609\/aaai.v40i11.37910"},{"key":"ref_4","unstructured":"Navaneet, K.L., Meibodi, K.P., Koohpayegani, S.A., and Pirsiavash, H. (October, January 29). CompGS: Smaller and faster Gaussian splatting with vector quantization. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy. Available online: https:\/\/arxiv.org\/abs\/2403.08550."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wang, K., Wen, K., Zhu, Z., Xu, D., and Wang, Z. (2023). LightGaussian: Unbounded 3D Gaussian compression with 15\u00d7 reduction and 200+ FPS. arXiv.","DOI":"10.52202\/079017-4447"},{"key":"ref_6","unstructured":"Xie, S., Zhang, W., Tang, C., Bai, Y., Lu, R., Ge, S., and Wang, Z. (October, January 29). MesonGS: Post-training compression of 3D Gaussians via efficient attribute transformation. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy."},{"key":"ref_7","unstructured":"Ali, M.S., Qamar, M., Bae, S.-H., and Tartaglione, E. (2024). Trimming the fat: Efficient compression of 3D Gaussian splats through pruning. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tian, B., Gao, Q., Xianyu, S., Cui, X., and Zhang, M. (2025). FlexGaussian: Flexible and cost-effective training-free compression for 3D Gaussian splatting. arXiv.","DOI":"10.1145\/3746027.3754744"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tang, L., Zhai, Y., Yang, J., Yang, C., and Wang, R. (2025, January 25\u201328). Feature prediction for 3D Gaussian splatting compression. Proceedings of the Data Compression Conference (DCC), Snowbird, UT, USA.","DOI":"10.1109\/DCC62719.2025.00015"},{"key":"ref_10","unstructured":"MPEG WG 7 and WG 4 (2024). JEE6.4 on collecting requirements and use cases for Gaussian splat coding (GSC), ISO\/IEC JTC 1\/SC 29\/WG 04, N0587."},{"key":"ref_11","unstructured":"MPEG WG 7 and WG 4 (2024). Description of JEE 6.3 on new technologies, ISO\/IEC JTC 1\/SC 29\/WG 04, N0586."},{"key":"ref_12","unstructured":"MPEG WG 7 and WG 4 (2024). Description on Joint Exploration Experiments 6: 3D Gaussian Representation and Compression, ISO\/IECJTC 1\/SC 29\/WG 04, N0560."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Li, Z., and Xu, Y. (2023). Spacetime Gaussian feature splatting for real-time dynamic view synthesis. arXiv.","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., and Wang, X. (2023). 4D Gaussian splatting for real-time dynamic scene rendering. arXiv.","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, H., Li, S., Gao, X., Batuer, A., Yu, L., and Liao, Y. (2025). GIFStream: 4D Gaussian-based immersive video with feature stream. arXiv.","DOI":"10.1109\/CVPR52734.2025.02027"},{"key":"ref_16","unstructured":"MPEG WG 7 (2025). Description of CEs to support Gaussian splats coding in G-PCC, ISO\/IEC JTC 1\/SC 29\/WG 7, N1344."},{"key":"ref_17","unstructured":"MPEG WG 7 (2025). Description of CEs for ISO\/IEC 23090-5 4th edition Amd1\u2014V-PCC for Gaussian splats, ISO\/IEC JTC 1\/SC 29\/WG7, N1343."},{"key":"ref_18","unstructured":"MPEG WG 7 and WG 4 (2025). JEE 6.7 on coordinating the 1F-vid track, ISO\/IEC JTC 1\/SC 29\/WG 7, N1278."},{"key":"ref_19","unstructured":"Morgenstern, W., Barthel, F., Hilsmann, A., and Eisert, P. (October, January 29). Compact 3D scene representation via self-organizing Gaussian grids. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","article-title":"Overview of the High Efficiency Video Coding (HEVC) standard","volume":"22","author":"Sullivan","year":"2012","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"122","DOI":"10.5573\/IEIESPC.2023.12.2.122","article-title":"Overview of versatile video coding (H.266\/VVC) and its coding performance analysis","volume":"12","author":"Lee","year":"2023","journal-title":"IEIE Trans. Smart Process. Comput."},{"key":"ref_22","unstructured":"MPEG WG 7 and WG 4 (2025). Common test conditions on Gaussian splat coding, ISO\/IEC JTC 1\/SC 29\/WG 04, N0655; Onlinemeeting."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1111\/cgf.14718","article-title":"Improved evaluation and generation of grid layouts using distance preservation quality and linear assignment sorting","volume":"42","author":"Barthel","year":"2023","journal-title":"Comput. Graph. Forum"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/TCOM.1982.1095471","article-title":"Vector quantization and predictive quantizers for Gauss\u2013Markov sources","volume":"30","author":"Gray","year":"1982","journal-title":"IEEE Trans. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product quantization for nearest neighbor search","volume":"33","author":"Douze","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4125\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:58:42Z","timestamp":1782867522000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":25,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134125"],"URL":"https:\/\/doi.org\/10.3390\/s26134125","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]}}}