GS-TG: 3D Gaussian Splatting Accelerator with Tile Grouping for Reducing Redundant Sorting while Preserving Rasterization Efficiency

3D Gaussian Splatting (3D-GS) has emerged as a promising alternative to neural radiance fields (NeRF) as it offers high speed as well as high image quality in novel view synthesis. Despite these advancements, 3D-GS still struggles to meet the frames per second (FPS) demands of real-time applications...

Full description

Saved in:
Bibliographic Details
Published in:2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 7
Main Authors: Jo, Joongho, Park, Jongsun
Format: Conference Proceeding
Language:English
Published: IEEE 22.06.2025
Subjects:
Accelerator
Energy efficiency
Gaussian Splatting
Hardware
Image quality
Neural radiance field
Optimization
Pipelines
Real-time systems
Rendering
Rendering (computer graphics)
Sorting
Three-dimensional displays
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract 3D Gaussian Splatting (3D-GS) has emerged as a promising alternative to neural radiance fields (NeRF) as it offers high speed as well as high image quality in novel view synthesis. Despite these advancements, 3D-GS still struggles to meet the frames per second (FPS) demands of real-time applications. In this paper, we introduce GS-TG, a tile-grouping-based accelerator that enhances 3D-GS rendering speed by reducing redundant sorting operations and preserving rasterization efficiency. GS-TG addresses a critical trade-off issue in 3D-GS rendering: increasing the tile size effectively reduces redundant sorting operations, but it concurrently increases unnecessary rasterization computations. So, during sorting of the proposed approach, GS-TG groups small tiles (for making large tiles) to share sorting operations across tiles within each group, significantly reducing redundant computations. During rasterization, a bitmask assigned to each Gaussian identifies relevant small tiles, to enable efficient sharing of sorting results. Consequently, GS-TG enables sorting to be performed as if a large tile size is used by grouping tiles during the sorting stage, while allowing rasterization to proceed with the original small tiles by using bitmasks in the rasterization stage. GS-TG is a lossless method requiring no retraining or fine-tuning and it can be seamlessly integrated with previous 3D-GS optimization techniques. Experimental results show that GS-TG achieves an average speed-up of 1.54 times over state-of-the-art 3D-GS accelerators.
AbstractList 3D Gaussian Splatting (3D-GS) has emerged as a promising alternative to neural radiance fields (NeRF) as it offers high speed as well as high image quality in novel view synthesis. Despite these advancements, 3D-GS still struggles to meet the frames per second (FPS) demands of real-time applications. In this paper, we introduce GS-TG, a tile-grouping-based accelerator that enhances 3D-GS rendering speed by reducing redundant sorting operations and preserving rasterization efficiency. GS-TG addresses a critical trade-off issue in 3D-GS rendering: increasing the tile size effectively reduces redundant sorting operations, but it concurrently increases unnecessary rasterization computations. So, during sorting of the proposed approach, GS-TG groups small tiles (for making large tiles) to share sorting operations across tiles within each group, significantly reducing redundant computations. During rasterization, a bitmask assigned to each Gaussian identifies relevant small tiles, to enable efficient sharing of sorting results. Consequently, GS-TG enables sorting to be performed as if a large tile size is used by grouping tiles during the sorting stage, while allowing rasterization to proceed with the original small tiles by using bitmasks in the rasterization stage. GS-TG is a lossless method requiring no retraining or fine-tuning and it can be seamlessly integrated with previous 3D-GS optimization techniques. Experimental results show that GS-TG achieves an average speed-up of 1.54 times over state-of-the-art 3D-GS accelerators.
Author Park, Jongsun
Jo, Joongho
Author_xml – sequence: 1
  givenname: Joongho
  surname: Jo
  fullname: Jo, Joongho
  email: jojoss1004@korea.ac.kr
  organization: Korea University,Seoul,Republic of Korea
– sequence: 2
  givenname: Jongsun
  surname: Park
  fullname: Park, Jongsun
  email: jongsun@korea.ac.kr
  organization: Korea University,Seoul,Republic of Korea
BookMark eNo1UM1OAjEQrokeFHkDY_oCi21n_-qNAK4mJBrBM5ktU2mydkm3SPDsg8uinma-v0m-uWLnvvXE2K0UIymFvpuOJzmUqR4pobIjJQFUCWdsqAtdAshMgEjLS_ZdLZJldc9hyivcdZ1DzxfbBmN0_p2PjaGGAsY28L2LG750DfEqtLttL9sj_UrrnelBv_g1-sgXbTil95ve_RKoo_B5smAXKbgvjK71fGatM468OVyzC4tNR8O_OWBvD7Pl5DGZP1dPk_E8QVnomECOGiUWoOvcFEJqQqo1gjk2sSZPlc2UwnVmMytKmddpKnMUUioq69pkFgbs5veuI6LVNrgPDIfV_3PgB1IuYHE
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133283
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore Digital Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133283
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-36a9a1a739b6c7019eaeb9a3c048fc642f522ad5f5f0816b4416a0112e8bbc5f3
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-36a9a1a739b6c7019eaeb9a3c048fc642f522ad5f5f0816b4416a0112e8bbc5f3
PageCount 7
ParticipantIDs ieee_primary_11133283
PublicationCentury 2000
PublicationDate 2025-June-22
PublicationDateYYYYMMDD 2025-06-22
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-22
  day: 22
PublicationDecade 2020
PublicationTitle 2025 62nd ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
Score 2.295305
Snippet 3D Gaussian Splatting (3D-GS) has emerged as a promising alternative to neural radiance fields (NeRF) as it offers high speed as well as high image quality in...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Accelerator
Energy efficiency
Gaussian Splatting
Hardware
Image quality
Neural radiance field
Optimization
Pipelines
Real-time systems
Rendering
Rendering (computer graphics)
Sorting
Three-dimensional displays
Title GS-TG: 3D Gaussian Splatting Accelerator with Tile Grouping for Reducing Redundant Sorting while Preserving Rasterization Efficiency
URI https://ieeexplore.ieee.org/document/11133283
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxcAEiCLe8sDqNi_bMVvVF1NV0SJ1q2znLJBQWrUp_AF-OD43BTEwsDnxRZHsXO58d993hNyDdUpxBwyyCFhW6ISZODPMxVIbJyEWkQnNJuR4nM_nalKD1QMWBgBC8Rm0cRhy-cXSbjFU1sG26Km3hw3SkFLswFo16jeOVKff7fmvKUP4ScLbe-FfbVOC1Rge__N9J6T1g7-jk2_LckoOoDwjn6Mpm40eaNqnI73dIPiRTldvOhQu06613oCEnDnF2CqdeXWnIbKE0941pU_I0ooXOPAn8bKi0-U6PP3xgtJYjoG_DhTRSKBQYzTpIPBMIEizRZ6Hg1nvkdU9FJj2qlaxVGilYy1TZYRF6nXQYJROrddcZ_3hw3kHTBfccYctOIz3joT2Op9AbozlLj0nzXJZwgWhRS6c05jztTwz3BjJjfdehIxtlCoLl6SFS7hY7WgyFvvVu_rj_jU5wo3CuqskuSHNar2FW3Jo36vXzfoubO4Xe72p4g
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5gIMEJEEO8yYFrtr7SLtymPRFjmliRdpuS1BFIqJu2Dv4AP5w460AcOHBLG1eVkrp2bH-fCbkFbYTgBhhEHrAokwFTfqSY8ROpTAJ-7CnXbCIZDhuTiRiVYHWHhQEAV3wGNRy6XH420ysMldWxLXpo7eE22eFRFHhruFaJ-_U9UW83W_Z7ihCAEvDaRvxX4xRnN7oH_3zjIan-IPDo6Nu2HJEtyI_JZ2_M0t4dDdu0J1dLhD_S8fxNutJl2tTamhCXNacYXaWpVXjqYks4bZ1T-oQ8rXiBA3sWzws6ni3c0x8vKI0FGfjzQBGJFAolSpN2HNMEwjSr5LnbSVt9VnZRYNIqW8HCWArpyyQUKtZIvg4SlJChtrprtD1-GOuCyYwbbrAJh7L-USyt1gfQUEpzE56QSj7L4ZTQrBEbIzHrq3mkuFIJV9Z_iRNfe6HQcEaquITT-ZooY7pZvfM_7t-QvX76OJgO7ocPF2QfNw2rsILgklSKxQquyK5-L16Xi2u30V98Ra0p
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%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=GS-TG%3A+3D+Gaussian+Splatting+Accelerator+with+Tile+Grouping+for+Reducing+Redundant+Sorting+while+Preserving+Rasterization+Efficiency&rft.au=Jo%2C+Joongho&rft.au=Park%2C+Jongsun&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133283&rft.externalDocID=11133283