{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multiscale-deep-context-modeling-for-lossless","title":"Multiscale deep context modeling for lossless point cloud geometry compression","arxiv_id":"2104.09859","date":"2021-04-20","proceeding":null,"authors":["Dat Thanh Nguyen","Maurice Quach","Giuseppe Valenzise","Pierre Duhamel"],"abstract":"We propose a practical deep generative approach for lossless point cloud geometry compression, called MSVoxelDNN, and show that it significantly reduces the rate compared to the MPEG G-PCC codec. Our previous work based on autoregressive models (VoxelDNN) has a fast training phase, however, inference is slow as the occupancy probabilities are predicted sequentially, voxel by voxel. In this work, we employ a multiscale architecture which models voxel occupancy in coarse-to-fine order. At each scale, MSVoxelDNN divides voxels into eight conditionally independent groups, thus requiring a single network evaluation per group instead of one per voxel. We evaluate the performance of MSVoxelDNN on a set of point clouds from Microsoft Voxelized Upper Bodies (MVUB) and MPEG, showing that the current method speeds up encoding/decoding times significantly compared to the previous VoxelDNN, while having average rate saving over G-PCC of 17.5%. The implementation is available at https://github.com/Weafre/MSVoxelDNN.","url_abs":"https://arxiv.org/abs/2104.09859v1","url_pdf":"https://arxiv.org/pdf/2104.09859v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multiscale-deep-context-modeling-for-lossless","repo_url":"https://github.com/Weafre/VoxelDNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"multiscale-deep-context-modeling-for-lossless","repo_url":"https://github.com/Weafre/MSVoxelDNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09859","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}