GSAcc: Accelerate 3D Gaussian Splatting via Depth Speculation and Gaussian-centric Rasterization

D Gaussian Splatting (3DGS) has emerged as a promising real-time photorealistic radiance field rendering technique. Existing GPU and hardware accelerators face limitations due to insufficient parallelism in sequential rendering pipeline stages and the memory overhead associated with interim results....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 62nd ACM/IEEE Design Automation Conference (DAC) s. 1 - 7
Hlavní autoři: Yang, Mengtian, Wang, Yipeng, Lo, Chieh-Pu, Zhang, Xiuhao, Oruganti, Sirish, Kulkarni, Jaydeep P.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 22.06.2025
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract D Gaussian Splatting (3DGS) has emerged as a promising real-time photorealistic radiance field rendering technique. Existing GPU and hardware accelerators face limitations due to insufficient parallelism in sequential rendering pipeline stages and the memory overhead associated with interim results. This paper presents GSAcc, a hardware accelerator co-designed with dataflow to render compressed 3DGS models on edge platforms efficiently. GSAcc enhances 3DGS rendering performance through several key innovations. First, it introduces Gaussian depth speculation, parallelizing preprocessing and sorting tasks. Second, GSAcc adopts a Gaussian-centric dataflow that interleaves preprocessing and rasterization, allowing all rendering steps to execute concurrently without storing intermediate results. Finally, it employs dedicated hardware acceleration to address sorting and rasterization bottlenecks within the optimized dataflow. We implemented and synthesized GSAcc using Intel16 PDK and evaluated its performance on real-world 3DGS scenes. Compared with desktop GPUs, GSAcc achieves up to 1.66 \times 10^{4} \mathrm{x} Power-Performance-Area (PPA) improvement as well as 48.7 x energy savings. Additionally, GSAcc outperforms the state-of-the-art hardware accelerator GSCore with up to 2.3x PPA improvement and 2.9x energy savings.
AbstractList D Gaussian Splatting (3DGS) has emerged as a promising real-time photorealistic radiance field rendering technique. Existing GPU and hardware accelerators face limitations due to insufficient parallelism in sequential rendering pipeline stages and the memory overhead associated with interim results. This paper presents GSAcc, a hardware accelerator co-designed with dataflow to render compressed 3DGS models on edge platforms efficiently. GSAcc enhances 3DGS rendering performance through several key innovations. First, it introduces Gaussian depth speculation, parallelizing preprocessing and sorting tasks. Second, GSAcc adopts a Gaussian-centric dataflow that interleaves preprocessing and rasterization, allowing all rendering steps to execute concurrently without storing intermediate results. Finally, it employs dedicated hardware acceleration to address sorting and rasterization bottlenecks within the optimized dataflow. We implemented and synthesized GSAcc using Intel16 PDK and evaluated its performance on real-world 3DGS scenes. Compared with desktop GPUs, GSAcc achieves up to 1.66 \times 10^{4} \mathrm{x} Power-Performance-Area (PPA) improvement as well as 48.7 x energy savings. Additionally, GSAcc outperforms the state-of-the-art hardware accelerator GSCore with up to 2.3x PPA improvement and 2.9x energy savings.
Author Kulkarni, Jaydeep P.
Oruganti, Sirish
Wang, Yipeng
Lo, Chieh-Pu
Zhang, Xiuhao
Yang, Mengtian
Author_xml – sequence: 1
  givenname: Mengtian
  surname: Yang
  fullname: Yang, Mengtian
  email: mengtian.yang@utexas.edu
  organization: The University of Texas at Austin
– sequence: 2
  givenname: Yipeng
  surname: Wang
  fullname: Wang, Yipeng
  email: yipeng.wang@utexas.edu
  organization: The University of Texas at Austin
– sequence: 3
  givenname: Chieh-Pu
  surname: Lo
  fullname: Lo, Chieh-Pu
  email: kcplo@utexas.edu
  organization: The University of Texas at Austin
– sequence: 4
  givenname: Xiuhao
  surname: Zhang
  fullname: Zhang, Xiuhao
  email: zhxhao007@utexas.edu
  organization: The University of Texas at Austin
– sequence: 5
  givenname: Sirish
  surname: Oruganti
  fullname: Oruganti, Sirish
  email: sirishoruganti@utexas.edu
  organization: The University of Texas at Austin
– sequence: 6
  givenname: Jaydeep P.
  surname: Kulkarni
  fullname: Kulkarni, Jaydeep P.
  email: jaydeep@austin.utexas.edu
  organization: The University of Texas at Austin
BookMark eNo9j9tKxDAYhCPoha77BiJ5ga45NE3jXWm1CguCq9fr3-SPBmq2tFlBn36Lp5sZ5mMYmDNyHHcRCbnkbMU5M1dNVReyzM1KMKFmxKVkUhyRpdGmlJIrJllenpKXdlNZe01nwR5HSEhlQ1vYT1OASDdDDymF-Eo_AtAGh_Q2M7T7GYddpBDdfzmzGNMYLH2EKeEYvr4r5-TEQz_h8tcX5Pn25qm-y9YP7X1drTPg2qQst75wpePCGweWedBeiK5wqJz2kgstuDVCl53tJOTMKttxcGqOzqoOQS7Ixc9uQMTtMIZ3GD-3f8flARtfVH4
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC63849.2025.11133032
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331503048
EndPage 7
ExternalDocumentID 11133032
Genre orig-research
GroupedDBID 6IE
6IH
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a179t-4cf6d8d12f9dac0fa7f22b6de5d7f312721c9278bcb3a40c5cb1ad5bcbdc5bea3
IEDL.DBID RIE
IngestDate Wed Oct 01 07:05:15 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a179t-4cf6d8d12f9dac0fa7f22b6de5d7f312721c9278bcb3a40c5cb1ad5bcbdc5bea3
PageCount 7
ParticipantIDs ieee_primary_11133032
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 2.2952235
Snippet D Gaussian Splatting (3DGS) has emerged as a promising real-time photorealistic radiance field rendering technique. Existing GPU and hardware accelerators face...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms 3D Gaussian Splatting
Accelerator Architecture
Energy conservation
Energy efficiency
Graphics processing units
Hardware acceleration
Pipelines
Radiance Field Rendering
Real-time systems
Rendering (computer graphics)
Software/Hardware Co-design
Sorting
Technological innovation
Three-dimensional displays
Title GSAcc: Accelerate 3D Gaussian Splatting via Depth Speculation and Gaussian-centric Rasterization
URI https://ieeexplore.ieee.org/document/11133032
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6UePCkRozv9OC1sNt9dNcbAcGDIUQ04Yaz02kkMQuBhd9vWxaMBw9emj4madJpO33MNx9jD8bYUwIW5CYvijhKQbgQIwIIlM5isk2eteRFDYfZZJKParC6x8IQkXc-o5bL-r98Pce1eyprO1p0u-XaHfdQKbUFa9Wo3zDI271O186m2MFPZNLaCf-iTfFWo3_yz_5OWfMHf8dHe8tyxg6oPGcfg3EH8ZHbxJoKF-GBRz0-gPXK4SD5ePEF3oeZb2bAe7SoPrkjl6_puTiUei8svEvmDPkruDgJNRSzyd77T2_dZ1HzIwiwy6gSMZpUZzqUJteAgQFlpCxSTYlWJgqlvdxhLlVWYBFBHKDVSQg6sUWNSUEQXbBGOS_pkvGUTKQC0llIZCUjCNLcnr0pk5gSElyxphue6WIbAmO6G5nrP-pv2LFTgvOpkvKWNarlmu7YEW6q2Wp57xX3DZBqne0
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4MmuhJjRjf9uB1Ybf79kZAwIiECCbccHY6jSRmIbDw-23LgvHgwUvTxyRNOm2nj_nmY-xBKX1KwIzM5EUn8CNwTIgRBwhimQSkmyxrSS_u95PxOB2UYHWLhSEi63xGNZO1f_lyhivzVFY3tOh6y9U77n4YBMLbwLVK3K_npvVWo6nnU2AAKCKsbcV_EadYu9E-_mePJ6z6g8Djg51tOWV7lJ-xj86wgfjIdaKNhYnxwP0W78BqaZCQfDj_AuvFzNdT4C2aF5_c0MuXBF0ccrkTdqxT5hT5G5hICSUYs8re20-jZtcpGRIc0AupcAJUkUykJ1QqAV0FsRIiiySFMla-J_T1DlMRJxlmPgQuaq14IENdlBhmBP45q-SznC4Yj0j5sUsy8Yi0pA9ulOrTNyUCI0KCS1Y1wzOZb4JgTLYjc_VH_T077I5ee5Pec__lmh0ZhRgPKyFuWKVYrOiWHeC6mC4Xd1aJ3_OxoTQ
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=GSAcc%3A+Accelerate+3D+Gaussian+Splatting+via+Depth+Speculation+and+Gaussian-centric+Rasterization&rft.au=Yang%2C+Mengtian&rft.au=Wang%2C+Yipeng&rft.au=Lo%2C+Chieh-Pu&rft.au=Zhang%2C+Xiuhao&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=7&rft_id=info:doi/10.1109%2FDAC63849.2025.11133032&rft.externalDocID=11133032