Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?

Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 44; no. 2
Main Authors: Celarek, A., Kopanas, G., Drettakis, G., Wimmer, M., Kerbl, B.
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.05.2025
Wiley
Subjects:
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray‐marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in‐depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
AbstractList Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray‐marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in‐depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
Abstract Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing real‐time novel‐view synthesis with high visual quality and fast training times. Neural Radiance Fields (NeRFs), which preceded 3DGS, are based on a principled ray‐marching approach for volumetric rendering. In contrast, while sharing a similar image formation model with NeRF, 3DGS uses a hybrid rendering solution that builds on the strengths of volume rendering and primitive rasterization. A crucial benefit of 3DGS is its performance, achieved through a set of approximations, in many cases with respect to volumetric rendering theory. A naturally arising question is whether replacing these approximations with more principled volumetric rendering solutions can improve the quality of 3DGS. In this paper, we present an in‐depth analysis of the various approximations and assumptions used by the original 3DGS solution. We demonstrate that, while more accurate volumetric rendering can help for low numbers of primitives, the power of efficient optimization and the large number of Gaussians allows 3DGS to outperform volumetric rendering despite its approximations.
Author Kerbl, B.
Kopanas, G.
Drettakis, G.
Wimmer, M.
Celarek, A.
Author_xml – sequence: 1
  givenname: A.
  surname: Celarek
  fullname: Celarek, A.
  organization: TU Wien
– sequence: 2
  givenname: G.
  orcidid: 0009-0002-5829-2192
  surname: Kopanas
  fullname: Kopanas, G.
  organization: Université Côte d'Azur
– sequence: 3
  givenname: G.
  orcidid: 0000-0002-9254-4819
  surname: Drettakis
  fullname: Drettakis, G.
  organization: Université Côte d'Azur
– sequence: 4
  givenname: M.
  orcidid: 0000-0002-9370-2663
  surname: Wimmer
  fullname: Wimmer, M.
  organization: TU Wien
– sequence: 5
  givenname: B.
  orcidid: 0000-0002-5168-8648
  surname: Kerbl
  fullname: Kerbl, B.
  organization: TU Wien
BackLink https://inria.hal.science/hal-05312577$$DView record in HAL
BookMark eNp1kE1Lw0AQhhepYK0e_AcBTx7azu5md5OLUlrbCkXBr-uy2UxqSprU3UTpvzc1oifnMsPwzMPwnpJeWZVIyAWFEW1rbNfZSAFwdkT6NJRqGEkR90gfaDsrEOKEnHq_AYBQSdEn17MKfcBnwcI03uemDJ52hanrvFwH94hpMLG2cabG4LUqmi3WLrfBI5Ypuha5OSPHmSk8nv_0AXmZ3z5Pl8PVw-JuOlkNLWcRG0YUgMmMKxPKjCVUWQvMRsLGcQIWU2vSRDA0WZhEqLiUTElLjQBqMi7Q8AG56rxvptA7l2-N2-vK5Ho5WenDDgSnTCj1QVv2smN3rnpv0Nd6UzWubN_TnHGqYirj6M9oXeW9w-xXS0EfotRtlPo7ypYdd-xnXuD-f1BPF_Pu4gsjQnRQ
Cites_doi 10.1007/978-3-031-72643-9_15
10.1145/3658193
10.1145/3528223.3530127
10.1109/CVPR46437.2021.00149
10.1109/2945.468400
10.1109/CVPR42600.2020.00749
10.1145/3550469.3555413
10.1145/3592426
10.1109/CVPR52688.2022.00539
10.1145/3592433
10.1145/3214834.3214880
10.1109/ACCESS.2024.3408318
10.1109/CVPR52733.2024.00512
10.1145/3687934
10.1109/ICCV48922.2021.00570
10.1109/TVCG.2002.1021576
10.1109/CVPR52733.2024.01839
ContentType Journal Article
Copyright 2025 The Author(s). Computer Graphics Forum published by Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
licence_http://creativecommons.org/publicdomain/zero
Copyright_xml – notice: 2025 The Author(s). Computer Graphics Forum published by Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.
– notice: 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: licence_http://creativecommons.org/publicdomain/zero
DBID 24P
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
1XC
VOOES
DOI 10.1111/cgf.70032
DatabaseName Wiley Online Library Open Access
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList CrossRef
Computer and Information Systems Abstracts


Database_xml – sequence: 1
  dbid: 24P
  name: Wiley Online Library Open Access
  url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1467-8659
EndPage n/a
ExternalDocumentID oai:HAL:hal-05312577v1
10_1111_cgf_70032
CGF70032
Genre article
GrantInformation_xml – fundername: ERC Advanced Grant FUNGRAPH
  funderid: 788065
– fundername: NVIDIA
– fundername: Adobe
GroupedDBID .3N
.4S
.DC
.GA
.Y3
05W
0R~
10A
15B
1OB
1OC
24P
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6J9
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
8VB
930
A03
AAESR
AAEVG
AAHQN
AAMMB
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABDPE
ABEML
ABPVW
ACAHQ
ACBWZ
ACCZN
ACFBH
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEFGJ
AEGXH
AEIGN
AEIMD
AEMOZ
AENEX
AEUYR
AEYWJ
AFBPY
AFEBI
AFFNX
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGXDD
AGYGG
AHBTC
AHEFC
AHQJS
AIDQK
AIDYY
AITYG
AIURR
AJXKR
AKVCP
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
EAD
EAP
EBA
EBO
EBR
EBS
EBU
EDO
EJD
EMK
EST
ESX
F00
F01
F04
F5P
FEDTE
FZ0
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K1G
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
P2W
P2X
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
QWB
R.K
RDJ
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
TH9
TN5
TUS
UB1
V8K
W8V
W99
WBKPD
WIH
WIK
WOHZO
WQJ
WXSBR
WYISQ
WZISG
XG1
ZL0
ZZTAW
~IA
~IF
~WT
AAYXX
AIQQE
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
1XC
VOOES
ID FETCH-LOGICAL-c3282-810026f37a46f2b17cc02c85c99b0cedcadb52eaf4b8e7366276c1a501af35ea3
IEDL.DBID 24P
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001466168900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-7055
IngestDate Fri Nov 28 06:21:30 EST 2025
Wed Aug 13 08:38:36 EDT 2025
Sat Nov 29 07:44:07 EST 2025
Mon Jul 21 09:51:54 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Ray tracing
CCS Concepts Computing methodologies → Image-based rendering Volumetric models Rasterization Ray tracing
Gaussians 3D Gaussian Splatting CCS Concepts
Volumetric models
Computing methodologies → Image-based rendering
Rasterization
Language English
License Attribution
licence_http://creativecommons.org/publicdomain/zero/: http://creativecommons.org/publicdomain/zero
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3282-810026f37a46f2b17cc02c85c99b0cedcadb52eaf4b8e7366276c1a501af35ea3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-9254-4819
0000-0002-9370-2663
0000-0002-5168-8648
0009-0002-5829-2192
OpenAccessLink https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.70032
PQID 3231791698
PQPubID 30877
PageCount 12
ParticipantIDs hal_primary_oai_HAL_hal_05312577v1
proquest_journals_3231791698
crossref_primary_10_1111_cgf_70032
wiley_primary_10_1111_cgf_70032_CGF70032
PublicationCentury 2000
PublicationDate May 2025
PublicationDateYYYYMMDD 2025-05-01
PublicationDate_xml – month: 05
  year: 2025
  text: May 2025
PublicationDecade 2020
PublicationPlace Oxford
PublicationPlace_xml – name: Oxford
PublicationTitle Computer graphics forum
PublicationYear 2025
Publisher Blackwell Publishing Ltd
Wiley
Publisher_xml – name: Blackwell Publishing Ltd
– name: Wiley
References 2023; 42
2010; 1
2023
2022
2021
2020
2002; 8
2019; 38
2018
2024; 43
2022; 41
2024; 4
2024
2024; 3
1995; 1
2021; 40
e_1_2_11_31_2
Max N. (e_1_2_11_19_2) 2010
e_1_2_11_13_2
e_1_2_11_12_2
e_1_2_11_11_2
e_1_2_11_33_2
e_1_2_11_10_2
e_1_2_11_32_2
e_1_2_11_6_2
e_1_2_11_28_2
e_1_2_11_5_2
e_1_2_11_27_2
e_1_2_11_4_2
e_1_2_11_25_3
e_1_2_11_26_2
e_1_2_11_3_2
e_1_2_11_25_2
e_1_2_11_2_2
Radl L. (e_1_2_11_24_2) 2024; 4
e_1_2_11_29_2
Kopanas G. (e_1_2_11_15_2) 2021
Yifan W. (e_1_2_11_30_2) 2019; 38
e_1_2_11_20_2
e_1_2_11_23_3
e_1_2_11_9_2
e_1_2_11_7_3
e_1_2_11_8_2
e_1_2_11_22_2
e_1_2_11_7_2
e_1_2_11_20_3
e_1_2_11_21_2
e_1_2_11_17_2
e_1_2_11_14_2
Lee J. (e_1_2_11_16_2) 2024; 3
e_1_2_11_19_3
e_1_2_11_18_2
Novák J. (e_1_2_11_23_2) 2018
References_xml – volume: 40
  start-page: 29
  year: 2021
  end-page: 43
  article-title: Point-based neural rendering with per-view optimization
– volume: 1
  start-page: 99
  issue: 2
  year: 1995
  end-page: 108
  article-title: Optical models for direct volume rendering
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– start-page: 7467
  year: 2020
  end-page: 7477
– volume: 1
  start-page: 259
  year: 2010
  end-page: 274
– volume: 42
  issue: 4
  year: 2023
  article-title: 3d gaussian splatting for real-time radiance field rendering
  publication-title: ACM Transactions on Graphics
– year: 2022
– volume: 41
  start-page: 102:1
  issue: 4
  year: 2022
  end-page: 102:15
  article-title: Instant neural graphics primitives with a multiresolution hash encoding
  publication-title: ACM Trans. Graph.
– start-page: 14:1
  year: 2018
  end-page: 14:1
  article-title: Monte carlo methods for physically based volume rendering
– volume: 3
  start-page: 497
  year: 2024
  end-page: 511
  article-title: Gscore: Efficient radiance field rendering via architectural support for 3d gaussian splatting
  publication-title: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume
– year: 2020
– year: 2021
– start-page: 1
  year: 2022
  end-page: 12
– year: 2023
– start-page: 1440
  year: 2021
  end-page: 1449
– year: 2024
– volume: 4
  issue: 43
  year: 2024
  article-title: StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
  publication-title: ACM Transactions on Graphics
– volume: 38
  issue: 6
  year: 2019
  article-title: Differentiable surface splatting for point-based geometry processing
  publication-title: ACM Transactions on Graphics (proceedings of ACM SIGGRAPH ASIA)
– volume: 43
  issue: 4
  year: 2024
  article-title: Smerf: Streamable memory efficient radiance fields for real-time large-scene exploration
  publication-title: ACM Trans. Graph.
– volume: 42
  issue: 4
  year: 2023
  article-title: Merf: Memory-efficient radiance fields for real-time view synthesis in unbounded scenes
  publication-title: ACM Trans. Graph.
– volume: 8
  start-page: 223
  issue: 3
  year: 2002
  end-page: 238
  article-title: Ewa splatting
  publication-title: IEEE Transactions on Visualization and Computer Graphics
– ident: e_1_2_11_11_2
  doi: 10.1007/978-3-031-72643-9_15
– ident: e_1_2_11_7_3
  doi: 10.1145/3658193
– ident: e_1_2_11_20_3
  doi: 10.1145/3528223.3530127
– ident: e_1_2_11_6_2
– ident: e_1_2_11_17_2
  doi: 10.1109/CVPR46437.2021.00149
– ident: e_1_2_11_20_2
  doi: 10.1145/3528223.3530127
– ident: e_1_2_11_18_2
  doi: 10.1109/2945.468400
– ident: e_1_2_11_26_2
  doi: 10.1109/CVPR42600.2020.00749
– ident: e_1_2_11_9_2
– ident: e_1_2_11_4_2
– ident: e_1_2_11_31_2
  doi: 10.1145/3550469.3555413
– start-page: 14:1
  volume-title: ACM SIGGRAPH 2018 Courses
  year: 2018
  ident: e_1_2_11_23_2
– ident: e_1_2_11_25_2
  doi: 10.1145/3592426
– ident: e_1_2_11_3_2
  doi: 10.1109/CVPR52688.2022.00539
– ident: e_1_2_11_14_2
  doi: 10.1145/3592433
– ident: e_1_2_11_7_2
  doi: 10.1145/3658193
– ident: e_1_2_11_33_2
– ident: e_1_2_11_19_3
– ident: e_1_2_11_25_3
  doi: 10.1145/3592426
– volume: 38
  issue: 6
  year: 2019
  ident: e_1_2_11_30_2
  article-title: Differentiable surface splatting for point-based geometry processing
  publication-title: ACM Transactions on Graphics (proceedings of ACM SIGGRAPH ASIA)
– ident: e_1_2_11_22_2
– ident: e_1_2_11_23_3
  doi: 10.1145/3214834.3214880
– ident: e_1_2_11_13_2
– volume: 4
  issue: 43
  year: 2024
  ident: e_1_2_11_24_2
  article-title: StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering
  publication-title: ACM Transactions on Graphics
– ident: e_1_2_11_8_2
  doi: 10.1109/ACCESS.2024.3408318
– ident: e_1_2_11_10_2
  doi: 10.1109/CVPR52733.2024.00512
– ident: e_1_2_11_21_2
  doi: 10.1145/3687934
– ident: e_1_2_11_2_2
– start-page: 259
  volume-title: Scientific Visualization: Advanced Concepts
  year: 2010
  ident: e_1_2_11_19_2
– start-page: 29
  volume-title: Computer Graphics Forum
  year: 2021
  ident: e_1_2_11_15_2
– ident: e_1_2_11_29_2
  doi: 10.1109/ICCV48922.2021.00570
– ident: e_1_2_11_32_2
  doi: 10.1109/TVCG.2002.1021576
– ident: e_1_2_11_12_2
– ident: e_1_2_11_28_2
  doi: 10.1109/CVPR52733.2024.01839
– ident: e_1_2_11_5_2
– ident: e_1_2_11_27_2
– volume: 3
  start-page: 497
  year: 2024
  ident: e_1_2_11_16_2
  article-title: Gscore: Efficient radiance field rendering via architectural support for 3d gaussian splatting
  publication-title: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume
SSID ssj0004765
Score 2.4627042
Snippet Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing...
Abstract Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene,...
SourceID hal
proquest
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
SubjectTerms Approximation
CCS Concepts
Computer Science
Computing methodologies → Image‐based rendering
Rasterization
Ray tracing
Rendering
Volumetric models
Title Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fcgf.70032
https://www.proquest.com/docview/3231791698
https://inria.hal.science/hal-05312577
Volume 44
WOSCitedRecordID wos001466168900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1467-8659
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004765
  issn: 0167-7055
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3PT8IwFG4UPOjB30YUSWM8eJmh67Z2MdEQcHAghKAYbkvbdWpigDDg7_e1bIgHExNvy_a2Lq_vff3avH5F6EZJHQL2Skfx1HU8HgIOMkodGlBF3RQIuLQ93WW9Hh-Nwv4Wui_2wqz0IdYLbiYzLF6bBBcy20hy9ZbeMYhJwN8yIZSZkHa9_vemSBb4hbC3kYzJZYVMGc_61R-D0fa7KYXc4JmbbNUON9HBv370EO3nLBM3VmFxhLb0-BjtbWgPnqCH1kRnmLZwWywys5MSP08_ha2Cxj0Y0nBDqYXRkcCvFsCMkj8e2IPnwOTxFA2jp5dmx8kPU3DA58CiudFaDVLKhBekriRMqbqruK_CUNaVTpRIpO9qkXqSa0aNLnygiPDrRKTU14KeodJ4MtbnCLt-kjASpprTwNNgRISmlMBneEJhwlJB14VX4-lKMyMu5hrgjNg6A4zA3-vnRuW60-jG5p7BBUAStiQVVC26I85zK4spUFIGrDaEhm6t439vJW62I3tx8XfTS7TrmkN-bVVjFZXms4W-QjtqOf_IZjUbZDVUbg2iYfcL5DfSag
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fS8MwED7mJqgP_hanU4P44EtlbdqmBVHG5jaxDpmb-FbSNFVBtrFu-_u9ZO2cD4LgW2mvTbncffkSLl8ALkQkfcTeyBBeYhm25yMOMkoN6lJBrQQJeKR7OmCdjvf66j8V4DrfCzPXh1gsuKnM0HitElwtSC9luXhLrhgGJQJwycYwcopQanSb_eB7XyRznVzbW6nGZMpCqpJn8fKP8WjlXVVDLlHNZcKqR5zm1v_-dRs2M6ZJavPQ2IGCHOzCxpL-4B7cNIYyJbRBWnyaqt2U5Hn0yXUlNOngsEZqQkyVlgR50SCm1PxJVx8-hya3-9Bv3vXqbSM7UMFAvyOT9pTeqptQxm03sSKTCVG1hOcI34-qQsaCx5FjSZ7YkScZVdrwrjC5UzV5Qh3J6QEUB8OBPARiOXHMTD-RHnVtiUYml5Sa-BkvpjhpKcN57tZwNNfNCPP5Bjoj1M5AI3T44rlSum7XglDdU9iAaMJmZhkqeX-EWX6lIUVaypDZ-tjQpfb8762E9VZTXxz93fQM1tq9xyAM7jsPx7BuqUN_dZVjBYqT8VSewKqYTT7S8WkWc1_B09ZH
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1dS8MwFA06RfTBb3E6NYgPvlTWpm1aEGVsdhNHGX6xt5CmiQqyjXXb7_cma2d9EATfSnvblJvck5Nw7wlCFyKRIWBvYolAOZYbhICDlBCL-EQQRwEBT0xPd2kcB_1-2FtC10UtzFwfYrHhpiPD4LUOcDlKVSnKxZu6ojAoAYBXXA8wVus6u73vqkjqe4Wyt9aMyXWFdB7P4tUfs9Hyu86FLBHNMl0180209b8_3UabOc_EjfnA2EFLcrCLNkrqg3vopjWUGSYt3ObTTNdS4qfRJzd50DiGSQ03hJhqJQn8aiBMa_njR3P0HJjc7qOX6O652bHy4xQs8Drw6ECrrfqKUO76yklsKkTdEYEnwjCpC5kKniaeI7lyk0BSopXhfWFzr25zRTzJyQGqDIYDeYiw46UptUMlA-K7EoxsLgmx4TNBSmDJUkXnhVvZaK6awYrVBjiDGWeAETh88VzrXHcaXabvaWQALKEzu4pqRX-wPLoyRoCUUuC1ITR0aTz_eyus2Y7MxdHfTc_QWq8Vse59_HCM1h194q9JcayhymQ8lSdoVcwmH9n41Ay4L6wS1DA
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=Does+3D+Gaussian+Splatting+Need+Accurate+Volumetric+Rendering%3F&rft.jtitle=Computer+graphics+forum&rft.au=Celarek%2C+A.&rft.au=Kopanas%2C+G.&rft.au=Drettakis%2C+G.&rft.au=Wimmer%2C+M.&rft.date=2025-05-01&rft.issn=0167-7055&rft.eissn=1467-8659&rft.volume=44&rft.issue=2&rft.epage=n%2Fa&rft_id=info:doi/10.1111%2Fcgf.70032&rft.externalDBID=10.1111%252Fcgf.70032&rft.externalDocID=CGF70032
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-7055&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-7055&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-7055&client=summon