Academic Journal
Adaptive spherical-harmonic allocation and saliency pruning for memory-efficient 3D Gaussian splatting.
| Τίτλος: | Adaptive spherical-harmonic allocation and saliency pruning for memory-efficient 3D Gaussian splatting. |
|---|---|
| Συγγραφείς: | Che, Xiaofeng1 (AUTHOR) binarystar671@foxmail.com, Wang, Chen1 (AUTHOR) cwang@cdut.edu.cn, Yao, Guangle1 (AUTHOR) yaoguangle19@cdut.edu.cn, Zhou, Haoran2 (AUTHOR) hr@sensing-sz.com, Ye, Shaoze2 (AUTHOR) 372767021@qq.com, Liu, Xulong3 (AUTHOR) liu.xulong@jingtian.com |
| Πηγή: | Visual Computer. Sep2026, Vol. 42 Issue 12, p1-19. 19p. |
| Θεματικοί όροι: | *Spherical harmonics, *Computer memory management, *Image quality in imaging systems |
| Περίληψη: | 3D Gaussian splatting (3DGS) has become a popular method for efficient and high-quality novel view synthesis. However, its training process demands excessive GPU memory, primarily due to uniform storage of high-order spherical-harmonic coefficients and rapid increases in the number of Gaussians. To address this, we introduce a memory-efficient approach that dynamically adjusts spherical-harmonic orders based on the expressive needs of each Gaussian and employs a saliency-based pruning strategy to remove redundant Gaussians. Our method reduces the peak GPU memory consumption during training by 29.6%, 29.8%, and 22.4% on the Mip-NeRF360, Tanks&Temples, and Deep Blending datasets, respectively, while maintaining rendering quality comparable to the original approach. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: | Academic Search Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://dx.doi.org/doi:10.1007/s00371-026-04702-9 Name: EDS - Springer Nature Journals (s7799221) Category: fullText Text: View record at Springer – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=01782789&ISBN=&volume=42&issue=12&date=20260915&spage=1&pages=1-19&title=Visual Computer&atitle=Adaptive%20spherical-harmonic%20allocation%20and%20saliency%20pruning%20for%20memory-efficient%203D%20Gaussian%20splatting.&aulast=Che%2C%20Xiaofeng&id=DOI:10.1007/s00371-026-04702-9 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: asx DbLabel: Academic Search Index An: 197191498 RelevancyScore: 1452 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1452.42785644531 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Adaptive spherical-harmonic allocation and saliency pruning for memory-efficient 3D Gaussian splatting. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Che%2C+Xiaofeng%22">Che, Xiaofeng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> binarystar671@foxmail.com</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Chen%22">Wang, Chen</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> cwang@cdut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yao%2C+Guangle%22">Yao, Guangle</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yaoguangle19@cdut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Haoran%22">Zhou, Haoran</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> hr@sensing-sz.com</i><br /><searchLink fieldCode="AR" term="%22Ye%2C+Shaoze%22">Ye, Shaoze</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> 372767021@qq.com</i><br /><searchLink fieldCode="AR" term="%22Liu%2C+Xulong%22">Liu, Xulong</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> liu.xulong@jingtian.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Visual+Computer%22">Visual Computer</searchLink>. Sep2026, Vol. 42 Issue 12, p1-19. 19p. – Name: Subject Label: Subject Terms Group: Su Data: *<searchLink fieldCode="DE" term="%22Spherical+harmonics%22">Spherical harmonics</searchLink><br />*<searchLink fieldCode="DE" term="%22Computer+memory+management%22">Computer memory management</searchLink><br />*<searchLink fieldCode="DE" term="%22Image+quality+in+imaging+systems%22">Image quality in imaging systems</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: 3D Gaussian splatting (3DGS) has become a popular method for efficient and high-quality novel view synthesis. However, its training process demands excessive GPU memory, primarily due to uniform storage of high-order spherical-harmonic coefficients and rapid increases in the number of Gaussians. To address this, we introduce a memory-efficient approach that dynamically adjusts spherical-harmonic orders based on the expressive needs of each Gaussian and employs a saliency-based pruning strategy to remove redundant Gaussians. Our method reduces the peak GPU memory consumption during training by 29.6%, 29.8%, and 22.4% on the Mip-NeRF360, Tanks&Temples, and Deep Blending datasets, respectively, while maintaining rendering quality comparable to the original approach. [ABSTRACT FROM AUTHOR] |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=197191498 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00371-026-04702-9 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 1 Subjects: – SubjectFull: Spherical harmonics Type: general – SubjectFull: Computer memory management Type: general – SubjectFull: Image quality in imaging systems Type: general Titles: – TitleFull: Adaptive spherical-harmonic allocation and saliency pruning for memory-efficient 3D Gaussian splatting. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Che, Xiaofeng – PersonEntity: Name: NameFull: Wang, Chen – PersonEntity: Name: NameFull: Yao, Guangle – PersonEntity: Name: NameFull: Zhou, Haoran – PersonEntity: Name: NameFull: Ye, Shaoze – PersonEntity: Name: NameFull: Liu, Xulong IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 09 Text: Sep2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 01782789 Numbering: – Type: volume Value: 42 – Type: issue Value: 12 Titles: – TitleFull: Visual Computer Type: main |
| ResultId | 1 |