Adaptive control for 3D Gaussian splatting: a systematic regularization framework.
Saved in:
| Title: | Adaptive control for 3D Gaussian splatting: a systematic regularization framework. |
|---|---|
| Authors: | Xiong, Wenxuan1 (AUTHOR), Wang, Fusheng1 (AUTHOR), Liu, Wenbin1 (AUTHOR), Li, Xing1 (AUTHOR), Zhu, Zhidong2 (AUTHOR), Xiong, Bangshu1,2 (AUTHOR), Rao, Zhibo1 (AUTHOR) raoxi36@foxmail.com |
| Source: | Visual Computer. Jun2026, Vol. 42 Issue 8, p1-16. 16p. |
| Abstract: | Regularization in 3D Gaussian Splatting (3D-GS) is often piecemeal, applying uniform penalties that fail to resolve the interdependent trade-offs between detail, smoothness, and stability. This paper moves beyond such ad hoc solutions by introducing a systematic, context-aware regularization framework for 3D Half-Gaussian Splatting (3D-HGS). Our method acts as an adaptive control system, featuring three synergistic techniques that respond to local scene properties and temporal dynamics. First, we introduce an adaptive opacity consistency loss that uses a dynamic, view-dependent geometric proxy to suppress appearance artifacts on smooth surfaces while preserving sharp boundaries. Second, a selective normal smoothness loss leverages a high-performance CUDA KNN search to enforce geometric coherence exclusively within object interiors, critically protecting edge and corner details from over-smoothing. Finally, a novel EMA-based normal anchoring mechanism provides temporal stability, safeguarding learned geometry against parameter drift during the volatile densification and pruning stages. Our integrated framework establishes a new state-of-the-art. Applied to the strong 3D-HGS baseline, it yields remarkable average PSNR gains, including an exceptional + 7.63 dB on the challenging Deep Blending dataset. These modular yet synergistic techniques offer a new, principled paradigm for robust and high-fidelity primitive-based rendering. Our source code is available at . [ABSTRACT FROM AUTHOR] |
| Copyright of Visual Computer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194407843 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Adaptive control for 3D Gaussian splatting: a systematic regularization framework. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Xiong%2C+Wenxuan%22">Xiong, Wenxuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Fusheng%22">Wang, Fusheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Wenbin%22">Liu, Wenbin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Xing%22">Li, Xing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhu%2C+Zhidong%22">Zhu, Zhidong</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xiong%2C+Bangshu%22">Xiong, Bangshu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Rao%2C+Zhibo%22">Rao, Zhibo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> raoxi36@foxmail.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Visual+Computer%22">Visual Computer</searchLink>. Jun2026, Vol. 42 Issue 8, p1-16. 16p. – Name: Abstract Label: Abstract Group: Ab Data: Regularization in 3D Gaussian Splatting (3D-GS) is often piecemeal, applying uniform penalties that fail to resolve the interdependent trade-offs between detail, smoothness, and stability. This paper moves beyond such ad hoc solutions by introducing a systematic, context-aware regularization framework for 3D Half-Gaussian Splatting (3D-HGS). Our method acts as an adaptive control system, featuring three synergistic techniques that respond to local scene properties and temporal dynamics. First, we introduce an adaptive opacity consistency loss that uses a dynamic, view-dependent geometric proxy to suppress appearance artifacts on smooth surfaces while preserving sharp boundaries. Second, a selective normal smoothness loss leverages a high-performance CUDA KNN search to enforce geometric coherence exclusively within object interiors, critically protecting edge and corner details from over-smoothing. Finally, a novel EMA-based normal anchoring mechanism provides temporal stability, safeguarding learned geometry against parameter drift during the volatile densification and pruning stages. Our integrated framework establishes a new state-of-the-art. Applied to the strong 3D-HGS baseline, it yields remarkable average PSNR gains, including an exceptional + 7.63 dB on the challenging Deep Blending dataset. These modular yet synergistic techniques offer a new, principled paradigm for robust and high-fidelity primitive-based rendering. Our source code is available at . [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Visual Computer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194407843 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00371-026-04532-9 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 16 StartPage: 1 Titles: – TitleFull: Adaptive control for 3D Gaussian splatting: a systematic regularization framework. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Xiong, Wenxuan – PersonEntity: Name: NameFull: Wang, Fusheng – PersonEntity: Name: NameFull: Liu, Wenbin – PersonEntity: Name: NameFull: Li, Xing – PersonEntity: Name: NameFull: Zhu, Zhidong – PersonEntity: Name: NameFull: Xiong, Bangshu – PersonEntity: Name: NameFull: Rao, Zhibo IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 01782789 Numbering: – Type: volume Value: 42 – Type: issue Value: 8 Titles: – TitleFull: Visual Computer Type: main |
| ResultId | 1 |
