Latent Space Slicing for Enhanced Entropy Modeling In Learning-Based Point Cloud Geometry Compression
The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research community and standardisation groups such as JP...
Uloženo v:
| Vydáno v: | Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) s. 4878 - 4882 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
23.05.2022
|
| Témata: | |
| ISSN: | 2379-190X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research community and standardisation groups such as JPEG and MPEG. Learned autoencoder architectures based on 3D convolutional layers are popular solutions and have demonstrated higher performance when adopting latent space entropy modeling based on learned hyperpriors. We propose an enhanced entropy model that takes into account both the hyperprior and previously encoded latent features to estimate the mean and scale of compressed features. The obtained results show a large increase in performance, with a BD PSNR gain of 5.75dB when compared to the Octree coding module in G-PCC for the D2 PSNR metric. We also perform an ablation study to quantify the impact of network parameters in the performance of the model, drawing useful insights for future research. |
|---|---|
| AbstractList | The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have been reporting increasingly better performance and are drawing the attention from the research community and standardisation groups such as JPEG and MPEG. Learned autoencoder architectures based on 3D convolutional layers are popular solutions and have demonstrated higher performance when adopting latent space entropy modeling based on learned hyperpriors. We propose an enhanced entropy model that takes into account both the hyperprior and previously encoded latent features to estimate the mean and scale of compressed features. The obtained results show a large increase in performance, with a BD PSNR gain of 5.75dB when compared to the Octree coding module in G-PCC for the D2 PSNR metric. We also perform an ablation study to quantify the impact of network parameters in the performance of the model, drawing useful insights for future research. |
| Author | Lazzarotto, Davi Frank, Nicolas Ebrahimi, Touradj |
| Author_xml | – sequence: 1 givenname: Nicolas surname: Frank fullname: Frank, Nicolas organization: École Polytechnique Fédérale de Lausanne (EPFL),Multimedia Signal Processing Group (MMSPG) – sequence: 2 givenname: Davi surname: Lazzarotto fullname: Lazzarotto, Davi organization: École Polytechnique Fédérale de Lausanne (EPFL),Multimedia Signal Processing Group (MMSPG) – sequence: 3 givenname: Touradj surname: Ebrahimi fullname: Ebrahimi, Touradj organization: École Polytechnique Fédérale de Lausanne (EPFL),Multimedia Signal Processing Group (MMSPG) |
| BookMark | eNotkFFLwzAUhaMouE1_gS_5A53JTZs0j1rmHFQcVMG3kSW3GumSktaH_ftVHFzuPXAPH5wzJ1chBiSEcrbknOmHTfXYNNtcaIAlsGlplatcywsy51IWOZtGXpIZCKUzrtnnDZkPww9jrFR5OSNYmxHDSJveWKRN560PX7SNia7CtwkW3STGFPsjfY0Ou7_vJtAaTQqTzp7MMFm20U-Mqou_jq4xHnBMR1rFQ59wGHwMt-S6Nd2Ad-e7IB_Pq_fqJavf1lOCOvNQiDGzuXJW700LlqHUFrDlDEG5Ym_QKaks6IJpEI7p1gIzpZISBCgo0RTciAW5_-d6RNz1yR9MOu7OlYgThnlZrg |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ICASSP43922.2022.9747496 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 1665405406 9781665405409 |
| EISSN | 2379-190X |
| EndPage | 4882 |
| ExternalDocumentID | 9747496 |
| Genre | orig-research |
| GroupedDBID | 23M 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i253t-c47dc9baf2c0e69c2ef10e27d5baed767c2950923d09fc20a8766232728ea51a3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 10 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000864187905034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:25:06 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i253t-c47dc9baf2c0e69c2ef10e27d5baed767c2950923d09fc20a8766232728ea51a3 |
| OpenAccessLink | https://infoscience.epfl.ch/handle/20.500.14299/189145 |
| PageCount | 5 |
| ParticipantIDs | ieee_primary_9747496 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-May-23 |
| PublicationDateYYYYMMDD | 2022-05-23 |
| PublicationDate_xml | – month: 05 year: 2022 text: 2022-May-23 day: 23 |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) |
| PublicationTitleAbbrev | ICASSP |
| PublicationYear | 2022 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0008748 |
| Score | 2.2780602 |
| Snippet | The growing adoption of point clouds as an imaging modality has stimulated the search for efficient solutions for compression. Learning-based algorithms have... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 4878 |
| SubjectTerms | compression deep learning entropy modeling Octrees Point cloud Point cloud compression Redundancy Three-dimensional displays Thresholding (Imaging) Training Transform coding |
| Title | Latent Space Slicing for Enhanced Entropy Modeling In Learning-Based Point Cloud Geometry Compression |
| URI | https://ieeexplore.ieee.org/document/9747496 |
| WOSCitedRecordID | wos000864187905034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA7b8KAXf2zib3LwaFyaNk1z1DF1MEZhCruNNnmZg9mO2gn77026OhW8eAkhkAQS-N6XvPe9h9A1eEJxlfqEGS5JwKkhlsdx4gmjLR_XWpgqz-xQjEbRZCLjBrrZamEAoAo-g1vXrXz5Olcr91XWddw3kGETNYUIN1qtLepGIoi-InWo7A56d-NxbK0tc2or29RzfxVRqWzIw_7_dj9AnW8xHo63ZuYQNSA7Qns_8gi2EQwtY8xKPLYPYMDjhfOWz7Clo7ifvVYuftspi3y5xq72mVOg40GG69yqM3JvTZnGcT63a_QW-UrjR8jfoCzW2OHFJlQ266CXh_5z74nU9RPInHG_JCoQWsk0MUxRCKViYDwKTGieJqBFKBSTli8wX1NpFKOJRUbLhphgESTcS_xj1MryDE4QZr7i2qfatwARWAyIdGpU6Nm1U-EpGpyitjuw6XKTImNan9XZ38PnaNfdiXPCM_8CtcpiBZdoR32U8_fiqrrXT3F7pNo |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA5zCurFH1P8bQ4erUvTpmmPOjY3rKOwCbuNNnmZg9mO2gn77026OhW8eAkhkAQS-N6XvPe9h9AN2FwwkTgWVSywXEaUpXkcs2yupObjUnJV5pkNeb_vj0ZBVEO3ay0MAJTBZ3BnuqUvX2ZiYb7Kmob7uoG3gTaZ61KyUmutcdfnrv8Vq0OCZq91PxhE2t5So7fSTTX7VxmV0op09v63_z46-pbj4WhtaA5QDdJDtPsjk2ADQag5Y1rggX4CAx7MjL98gjUhxe30tXTy606RZ_MlNtXPjAYd91JcZVedWA_amEkcZVO9RmuWLSR-hOwNinyJDWKsgmXTI_TSaQ9bXauqoGBNKXMKS7hciiCJFRUEvEBQUDYByiVLYpDc44IGmjFQR5JACUpijY2aD1FOfYiZHTvHqJ5mKZwgTB3BpEOkoyHC1Sjgy0QJz9ZrJ9wWxD1FDXNg4_kqSca4Oquzv4ev0XZ3-ByOw17_6RztmPsxLnnqXKB6kS_gEm2Jj2L6nl-Vd_wJMbqoIQ |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Latent+Space+Slicing+for+Enhanced+Entropy+Modeling+In+Learning-Based+Point+Cloud+Geometry+Compression&rft.au=Frank%2C+Nicolas&rft.au=Lazzarotto%2C+Davi&rft.au=Ebrahimi%2C+Touradj&rft.date=2022-05-23&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=4878&rft.epage=4882&rft_id=info:doi/10.1109%2FICASSP43922.2022.9747496&rft.externalDocID=9747496 |