Self-augmented Gaussian Splatting with Structure-aware Masks for Sparse-view 3D Reconstruction
Sparse-view 3D reconstruction stands as a formidable challenge in computer vision, aiming to build complete three-dimensional models from a limited array of viewing perspectives. This task confronts several difficulties: 1) the limited number of input images that lack consistent information; 2) depe...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
14.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Sparse-view 3D reconstruction stands as a formidable challenge in computer vision, aiming to build complete three-dimensional models from a limited array of viewing perspectives. This task confronts several difficulties: 1) the limited number of input images that lack consistent information; 2) dependence on the quality of input images; and 3) the substantial size of model parameters. To address these challenges, we propose a self-augmented coarse-to-fine Gaussian splatting paradigm, enhanced with a structure-aware mask, for sparse-view 3D reconstruction. In particular, our method initially employs a coarse Gaussian model to obtain a basic 3D representation from sparse-view inputs. Subsequently, we develop a fine Gaussian network to enhance consistent and detailed representation of the output with both 3D geometry augmentation and perceptual view augmentation. During training, we design a structure-aware masking strategy to further improve the model's robustness against sparse inputs and noise.Experimental results on the MipNeRF360 and OmniObject3D datasets demonstrate that the proposed method achieves state-of-the-art performances for sparse input views in both perceptual quality and efficiency. |
---|---|
AbstractList | Sparse-view 3D reconstruction stands as a formidable challenge in computer vision, aiming to build complete three-dimensional models from a limited array of viewing perspectives. This task confronts several difficulties: 1) the limited number of input images that lack consistent information; 2) dependence on the quality of input images; and 3) the substantial size of model parameters. To address these challenges, we propose a self-augmented coarse-to-fine Gaussian splatting paradigm, enhanced with a structure-aware mask, for sparse-view 3D reconstruction. In particular, our method initially employs a coarse Gaussian model to obtain a basic 3D representation from sparse-view inputs. Subsequently, we develop a fine Gaussian network to enhance consistent and detailed representation of the output with both 3D geometry augmentation and perceptual view augmentation. During training, we design a structure-aware masking strategy to further improve the model's robustness against sparse inputs and noise.Experimental results on the MipNeRF360 and OmniObject3D datasets demonstrate that the proposed method achieves state-of-the-art performances for sparse input views in both perceptual quality and efficiency. |
Author | Meng, Lingbei Hu, Wei Du, Bi'an |
Author_xml | – sequence: 1 givenname: Lingbei surname: Meng fullname: Meng, Lingbei – sequence: 2 givenname: Bi'an surname: Du fullname: Du, Bi'an – sequence: 3 givenname: Wei surname: Hu fullname: Hu, Wei |
BookMark | eNqNyssOATEUgOFGSFzfoYl1k2rnwtp1Y2OsyQlnRhktPa15fSIewOpf_F-fta2z2GI9pfVETBOlumxEdJVSqixXaap77FBgXQqI1R1twDNfQyQyYHnxqCEEYyvemHDhRfDxFKJHAQ145FugG_HS-Q8ETyheBhuuF3yHJ2fpq42zQ9YpoSYc_Tpg49VyP9-Ih3fPiBSOVxe9_ayjljMl8yRTmf5PvQEDlUYw |
ContentType | Paper |
Copyright | 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_30920746263 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 22:16:00 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_30920746263 |
OpenAccessLink | https://www.proquest.com/docview/3092074626?pq-origsite=%requestingapplication% |
PQID | 3092074626 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_3092074626 |
PublicationCentury | 2000 |
PublicationDate | 20240814 |
PublicationDateYYYYMMDD | 2024-08-14 |
PublicationDate_xml | – month: 08 year: 2024 text: 20240814 day: 14 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.564478 |
SecondaryResourceType | preprint |
Snippet | Sparse-view 3D reconstruction stands as a formidable challenge in computer vision, aiming to build complete three-dimensional models from a limited array of... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Computer vision Image enhancement Image quality Image reconstruction Representations Three dimensional models |
Title | Self-augmented Gaussian Splatting with Structure-aware Masks for Sparse-view 3D Reconstruction |
URI | https://www.proquest.com/docview/3092074626 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NS8MwFH-4FcGbn_gxR0CvwTbp-nES1HZD6BhWYSdH2qYeHF3XWLz5t_sSOncQdgwJ4SWU9_vl917fA7hlyAECz86oXzKfupntU2FnNs3dYBR6Mgxy084nmXqTN_d5Ppp3gpvq0io3PtE46mKVa438jtsh070xmHdfr6nuGqWjq10LjR5YzHF1mNZ6iKazlz-VhXk-cmb-z9Ea9IgPwZqJWjZHsCerY9g3SZe5OoH3VC5LKtoPUxizIGPRKv1PI0nrpTD5yETLpCQ1NV7bRlLxLRpJEqE-FUG2iQvxXSqpNp3wJ6LfktuKsKdwE0evjxO6MWrRfThqsT0mP4N-tarkORCEmYw7CDUc6Q8yfFE6Mgt4XpY6cFywCxjs2uly9_QVHDBEai2UOu4A-milvEak_cqG0Avi8bC7VBwlP9EvZguI4A |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8QwEB60RfTmEx-rBvQabJNuHydB3bXqtix2hT1Zkm7qwaVbG4t_3yR03YOw54QwCWG-b75MZgCuieIAoe9wHJQkwB53Aswc7uDCC_uRL6KwMO18ktSP37znaX_aCW6yS6tc-kTjqGeLQmvkN9SJiO6NQfzb-gvrrlH6dbVrobEJti65GVpg3w3S8eufykL8QHFm-s_RGvQY7oI9ZrVo9mBDVPuwZZIuC3kA75mYl5i1H6Yw5gw9slbqP40oq-fM5CMjLZOizNR4bRuB2Q9rBEqY_JRIsU01UcWlAmvTEX1AOpZcVYQ9hKvhYHIf46VReXdxZL7aJj0Cq1pU4hiQghlOXQU1VNEfxfBZ6Qoe0qIs9cPxjJxAb91Kp-uHL2E7niSjfPSUvpzBDlGorUVT1-uBpSwW5wp1v_lFd7S_jcaJvw |
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=article&rft.atitle=Self-augmented+Gaussian+Splatting+with+Structure-aware+Masks+for+Sparse-view+3D+Reconstruction&rft.jtitle=arXiv.org&rft.au=Meng%2C+Lingbei&rft.au=Du%2C+Bi%27an&rft.au=Hu%2C+Wei&rft.date=2024-08-14&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |