pith. sign in

arxiv: 2401.03890 · v9 · submitted 2024-01-08 · 💻 cs.CV · cs.AI· cs.GR· cs.MM

A Survey on 3D Gaussian Splatting

Guikun Chen , Wenguan Wang This is my paper

Pith reviewed 2026-05-24 04:15 UTC · model grok-4.3

classification 💻 cs.CV cs.AIcs.GRcs.MM
keywords 3D Gaussian SplattingRadiance FieldsExplicit Scene RepresentationReal-time RenderingDifferentiable Rendering3D ReconstructionVirtual RealityScene Editing
0
0 comments X

The pith

3D Gaussian splatting represents scenes explicitly with millions of learnable 3D Gaussians to deliver real-time rendering and direct editability.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper supplies the first systematic overview of 3D Gaussian splatting as an explicit alternative to implicit neural radiance fields. It traces the core principles of using millions of optimized 3D Gaussians together with a differentiable rendering process. This explicit approach yields rendering speeds orders of magnitude faster than neural methods while allowing straightforward scene edits. The survey evaluates leading models on standard benchmarks, catalogs emerging applications in virtual reality and interactive media, and flags open challenges for future work.

Core claim

3D Gaussian splatting has emerged as a transformative technique in radiance fields by replacing implicit neural models with an explicit scene representation consisting of millions of learnable 3D Gaussians, which when paired with a differentiable rendering algorithm produces real-time performance and unprecedented editability.

What carries the argument

Explicit representation by millions of learnable 3D Gaussians combined with a differentiable splatting renderer that optimizes directly on the Gaussians without an underlying neural network.

If this is right

  • Real-time rendering becomes feasible for virtual reality and interactive media applications.
  • Direct editability of scene elements becomes practical without retraining.
  • Comparative evaluations across benchmarks reveal relative strengths of individual 3D GS variants.
  • Current limitations point to specific directions for extending explicit radiance-field methods.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Developers of 3D content pipelines may shift from neural to Gaussian-based storage formats for faster iteration.
  • Scaling questions around memory use for very large environments remain open for direct measurement.
  • Hybrid systems that combine Gaussian splatting with sparse neural components could be tested on dynamic scenes.

Load-bearing premise

The survey's selection of models and benchmarks is representative enough to support claims about performance and practical utility across the field.

What would settle it

Publication of a large-scale independent benchmark in which implicit neural methods consistently match or exceed 3D Gaussian splatting in both rendering speed and editability on the same tasks would undermine the survey's central positioning of the technique.

Figures

Figures reproduced from arXiv: 2401.03890 by Guikun Chen, Wenguan Wang.

Figure 1
Figure 1. Figure 1: The number of published papers and official GitHub [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Structure of the overall review. This format allows for a differentiable and compact representation of complex scenes, albeit often at the cost of high computational load due to volumetric ray marching. Note that typically, the color 𝑐 is direction-dependent, whereas the volume density 𝜎 is not [154]. • Explicit Radiance Field. An explicit radiance field directly represents the distribution of light in a d… view at source ↗
Figure 3
Figure 3. Figure 3: An illustration of the forward process of 3D GS (see Sec. [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: NeRFs vs. 3D GS. (a) NeRF samples along the ray and then queries the MLP to obtain colors and densities, which can be seen as a backward mapping (ray tracing). (b) 3D GS projects all 3D Gaussians into the image space (i.e., splatting) and then performs parallel rendering, which can be viewed as a forward mapping (rasterization). sampling 3D space points per pixel. Such a paradigm struggles with high-resolu… view at source ↗
Figure 5
Figure 5. Figure 5: An illustration of the tile based parallel (at the pixel-level) [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Typical applications benefited from GS (Sec. [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

3D Gaussian splatting (GS) has emerged as a transformative technique in radiance fields. Unlike mainstream implicit neural models, 3D GS uses millions of learnable 3D Gaussians for an explicit scene representation. Paired with a differentiable rendering algorithm, this approach achieves real-time rendering and unprecedented editability, making it a potential game-changer for 3D reconstruction and representation. In the present paper, we provide the first systematic overview of the recent developments and critical contributions in 3D GS. We begin with a detailed exploration of the underlying principles and the driving forces behind the emergence of 3D GS, laying the groundwork for understanding its significance. A focal point of our discussion is the practical applicability of 3D GS. By enabling unprecedented rendering speed, 3D GS opens up a plethora of applications, ranging from virtual reality to interactive media and beyond. This is complemented by a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks to highlight their performance and practical utility. The survey concludes by identifying current challenges and suggesting potential avenues for future research. Through this survey, we aim to provide a valuable resource for both newcomers and seasoned researchers, fostering further exploration and advancement in explicit radiance field.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The manuscript is a survey on 3D Gaussian Splatting (3D GS) that claims to deliver the first systematic overview of the technique. It covers the underlying principles and motivations for its emergence as an explicit alternative to implicit neural radiance fields, discusses practical applications enabled by real-time rendering and editability (e.g., VR and interactive media), presents a comparative analysis of leading 3D GS models evaluated on benchmark tasks, and concludes with current challenges and future research directions.

Significance. A well-executed survey with transparent methodology and reproducible comparative tables could consolidate the fast-moving 3D GS literature and serve as an entry point for newcomers while highlighting performance trade-offs. The explicit-representation angle and real-time claims are timely for the CV/graphics community, but the significance is limited by the absence of disclosed selection criteria for the 'leading models' and benchmarks.

major comments (1)
  1. [Abstract, §1] Abstract and §1 (Introduction): The central claim that the paper supplies 'the first systematic overview' together with 'a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks' is load-bearing. No explicit inclusion/exclusion criteria, search strategy, or completeness assessment for the selected papers or benchmarks is described. This renders the comparative results non-reproducible and vulnerable to selection bias.
minor comments (1)
  1. [Abstract] The abstract and introduction repeatedly use 'unprecedented editability' and 'game-changer' without quantifying the editability gains relative to prior explicit or implicit methods; a short table contrasting editability operations would improve clarity.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our survey. We agree that explicitly documenting the literature selection process will improve transparency and address concerns about reproducibility and bias. We will revise the manuscript to incorporate a dedicated methodology description.

read point-by-point responses

  1. Referee: [Abstract, §1] Abstract and §1 (Introduction): The central claim that the paper supplies 'the first systematic overview' together with 'a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks' is load-bearing. No explicit inclusion/exclusion criteria, search strategy, or completeness assessment for the selected papers or benchmarks is described. This renders the comparative results non-reproducible and vulnerable to selection bias.

    Authors: We acknowledge the validity of this observation. The current manuscript does not detail the search strategy, databases, keywords, or inclusion/exclusion criteria used to identify papers and benchmarks. In the revised version, we will insert a new subsection 'Survey Methodology' early in §1 (and reference it in the abstract) that specifies: (1) search databases (arXiv, Google Scholar, CVPR/ICCV/ECCV proceedings), (2) keywords and Boolean combinations, (3) date range, (4) inclusion criteria (direct relevance to 3D Gaussian Splatting primitives or rendering, citation impact or novelty), and (5) how the 'leading models' and standard benchmarks (e.g., NeRF, Tanks & Temples) were chosen. This addition will make the comparative tables reproducible and mitigate selection-bias concerns while preserving the survey's scope and claims. revision: yes

Circularity Check

0 steps flagged

Survey paper contains no derivations, predictions, or fitted quantities; no circularity present

full rationale

This paper is a literature review surveying developments in 3D Gaussian Splatting. It contains no mathematical derivations, equations, predictions of new quantities, fitted parameters, or self-referential reasoning chains. The abstract and structure describe an overview of principles, applications, and comparisons of existing models, with no load-bearing steps that reduce to inputs by construction, self-citation, or renaming. As a result, none of the enumerated circularity patterns apply, and the paper is self-contained as a descriptive survey.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This survey paper contains no free parameters, axioms, or invented entities as it does not present original mathematical or empirical work.

pith-pipeline@v0.9.0 · 5751 in / 1176 out tokens · 23897 ms · 2026-05-24T04:15:19.763804+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

    cs.CV 2026-05 unverdicted novelty 7.0

    PairDropGS applies paired dropout-induced low-frequency consistency regularization and progressive scheduling to improve stability and quality in sparse-view 3D Gaussian Splatting over prior dropout methods.

  2. HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis

    cs.GR 2026-05 unverdicted novelty 7.0

    HairGPT reframes 3D hairstyle synthesis as dual-decoupled autoregressive strand sequence modeling with geometric tokenization for semantic control and rare style generation.

  3. GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting

    cs.LG 2026-05 unverdicted novelty 7.0

    GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.

  4. Planar Gaussian Splatting with Bilinear Spatial Transformer for Wireless Radiance Field Reconstruction

    eess.SP 2026-04 unverdicted novelty 7.0

    BiSplat-WRF applies 2D planar Gaussians rendered on angular domains plus a bilinear spatial transformer to capture electromagnetic interactions, outperforming prior NeRF and GS methods on SSIM for wireless radiance fi...

  5. DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 7.0

    DOC-GS uses dual-domain calibration with continuous depth-guided dropout in optimization and dark channel prior evidence in observation to model and prune unreliable Gaussians, reducing haze and distortions in sparse-...

  6. PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

    cs.CV 2026-05 unverdicted novelty 6.0

    PairDropGS uses paired dropout with low-frequency consistency regularization and progressive scheduling to stabilize and improve sparse-view 3D Gaussian Splatting.

  7. Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training

    cs.CV 2026-04 conditional novelty 6.0

    A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.

  8. ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation

    cs.CV 2026-04 unverdicted novelty 6.0

    ESCAPE combines spatio-temporal fusion mapping for depth-free 3D memory with a memory-driven grounding module and adaptive execution policy to reach 65.09% success on ALFRED test-seen long-horizon mobile manipulation tasks.

  9. GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors

    cs.CV 2026-04 unverdicted novelty 6.0

    GS4City derives geometry-grounded semantic masks from LoD3 CityGML models via raycasting and fuses them with 2D foundation model outputs to supervise identity encodings on Gaussians, improving coarse and fine semantic...

  10. PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting

    cs.CV 2026-04 unverdicted novelty 6.0

    PointSplat uses 3D-geometry-only pruning and a dual-branch transformer to reduce Gaussian count in 3DGS scenes, delivering competitive quality and better efficiency without per-scene fine-tuning.

  11. A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

    cs.CV 2025-08 unverdicted novelty 3.0

    A survey that categorizes and summarizes methods applying 3D Gaussian Splatting to segmentation, editing, generation, and related tasks, including datasets and evaluation protocols.

  12. NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results

    cs.CV 2026-04 unverdicted novelty 2.0

    The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · cited by 11 Pith papers · 4 internal anchors

  1. [1]

    Rameen Abdal, Wang Yifan, Zifan Shi, Yinghao Xu, Ryan Po, Zhengfei Kuang, Qifeng Chen, Dit-Yan Yeung, and Gordon Wetzstein. 2024. Gaussian Shell Maps for Efficient 3D Human Generation. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  2. [2]

    Jad Abou-Chakra, Krishan Rana, Feras Dayoub, and Niko Sünderhauf. 2024. Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics. In Proc. Annu. Conf. Robot Learn

    work page 2024

  3. [3]

    Rachel Albert, Anjul Patney, David Luebke, and Joohwan Kim. 2017. Latency requirements for foveated rendering in virtual reality. ACM Transactions on Applied Perception 14, 4 (2017), 1–13

    work page 2017

  4. [4]

    Kara-Ali Aliev, Artem Sevastopolsky, Maria Kolos, Dmitry Ulyanov, and Victor Lempitsky. 2020. Neural point-based graphics. InProc. Eur. Conf. Comput. Vis. 696–712

    work page 2020

  5. [5]

    Max Allan, Jonathan Mcleod, Congcong Wang, Jean Claude Rosenthal, Zhenglei Hu, Niklas Gard, Peter Eisert, Ke Xue Fu, Trevor Zeffiro, Wenyao Xia, et al. 2021. Stereo correspondence and reconstruction of endoscopic data challenge. arXiv preprint arXiv:2101.01133 (2021)

    work page arXiv 2021

  6. [6]

    Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt, and Gerard Pons-Moll. 2018. Video based reconstruction of 3d people models. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 8387–8397

    work page 2018

  7. [7]

    Jeongmin Bae, Seoha Kim, Youngsik Yun, Hahyun Lee, Gun Bang, and Youngjung Uh. 2024. Per-Gaussian Embedding-Based Deformation for Deformable 3D Gaussian Splatting. arXiv preprint arXiv:2404.03613 (2024)

    work page arXiv 2024

  8. [8]

    Yanqi Bao, Tianyu Ding, Jing Huo, Yaoli Liu, Yuxin Li, Wenbin Li, Yang Gao, and Jiebo Luo. 2024. 3d gaussian splatting: Survey, technologies, challenges, and opportunities. arXiv preprint arXiv:2407.17418 (2024)

    work page arXiv 2024

  9. [9]

    Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2022. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 5470–5479

    work page 2022

  10. [10]

    Florian Barthel, Arian Beckmann, Wieland Morgenstern, Anna Hilsmann, and Peter Eisert. 2024. Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Worksh

    work page 2024

  11. [11]

    Luis Bolanos, Shih-Yang Su, and Helge Rhodin. 2024. Gaussian Shadow Casting for Neural Characters. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  12. [12]

    Sierra Bonilla, Shuai Zhang, Dimitrios Psychogyios, Danail Stoyanov, Francisco Vasconcelos, and Sophia Bano. 2024. Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction. arXiv preprint arXiv:2404.06128 (2024)

    work page arXiv 2024

  13. [13]

    Piotr Borycki, Weronika Smolak, Joanna Waczyńska, Marcin Mazur, Sławomir Tadeja, and Przemysław Spurek. 2024. GASP: Gaussian Splatting for Physic-Based Simulations. arXiv preprint arXiv:2409.05819 (2024)

    work page arXiv 2024

  14. [14]

    Chris Buehler, Michael Bosse, Leonard McMillan, Steven Gortler, and Michael Cohen. 2023. Unstructured lumigraph rendering. InSeminal Graphics Papers: Pushing the Boundaries, Volume 2 . 497–504

    work page 2023

  15. [15]

    Holger Caesar, Varun Bankiti, Alex H Lang, Sourabh Vora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Giancarlo Baldan, and Oscar Beijbom. 2020. nuscenes: A multimodal dataset for autonomous driving. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 11621–11631

    work page 2020

  16. [16]

    Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang, Xiaokang Yang, Zongwei Zhou, and Alan Yuille. 2024. Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis. In Proc. Eur. Conf. Comput. Vis

    work page 2024

  17. [17]

    Yuanhao Cai, Jiahao Wang, Alan Yuille, Zongwei Zhou, and Angtian Wang. 2024. Structure-aware sparse-view x-ray 3d reconstruction. InProc. IEEE Conf. Comput. Vis. Pattern Recognit. 11174–11183

    work page 2024

  18. [18]

    Ang Cao and Justin Johnson. 2023. Hexplane: A fast representation for dynamic scenes. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 130–141

    work page 2023

  19. [19]

    Jiazhong Cen, Jiemin Fang, Chen Yang, Lingxi Xie, Xiaopeng Zhang, Wei Shen, and Qi Tian. 2023. Segment Any 3D Gaussians. arXiv preprint arXiv:2312.00860 (2023)

    work page arXiv 2023

  20. [20]

    Jiahao Chang, Yinglin Xu, Yihao Li, Yuantao Chen, and Xiaoguang Han. 2024. GaussReg: Fast 3D Registration with Gaussian Splatting. In Proc. Eur. Conf. Comput. Vis

    work page 2024

  21. [21]

    David Charatan, Sizhe Li, Andrea Tagliasacchi, and Vincent Sitzmann. 2024. pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  22. [22]

    Anpei Chen, Haofei Xu, Stefano Esposito, Siyu Tang, and Andreas Geiger. 2024. LaRa: Efficient Large-Baseline Radiance Fields. arXiv preprint arXiv:2407.04699 (2024)

    work page arXiv 2024

  23. [23]

    Hanlin Chen, Chen Li, and Gim Hee Lee. 2023. NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance.arXiv preprint arXiv:2312.00846 (2023)

    work page arXiv 2023

  24. [24]

    Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, and Guosheng Lin. 2024. GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  25. [25]

    Yufan Chen, Lizhen Wang, Qijing Li, Hongjiang Xiao, Shengping Zhang, Hongxun Yao, and Yebin Liu. 2023. MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar. arXiv preprint arXiv:2312.04558 (2023)

    work page arXiv 2023

  26. [26]

    Yihang Chen, Qianyi Wu, Jianfei Cai, Mehrtash Harandi, and Weiyao Lin. 2024. HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression. In Proc. Eur. Conf. Comput. Vis

    work page 2024

  27. [27]

    Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, and Jianfei Cai. 2024. MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images. In Proc. Eur. Conf. Comput. Vis

    work page 2024

  28. [28]

    Zilong Chen, Feng Wang, and Huaping Liu. 2024. Text-to-3d using gaussian splatting. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Manuscript submitted to ACM A Survey on 3D Gaussian Splatting 25

    work page 2024

  29. [29]

    Kai Cheng, Xiaoxiao Long, Kaizhi Yang, Yao Yao, Wei Yin, Yuexin Ma, Wenping Wang, and Xuejin Chen. 2024. GaussianPro: 3D Gaussian Splatting with Progressive Propagation. In Proc. ACM Int. Conf. Mach. Learn

    work page 2024

  30. [30]

    Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, and Hoseok Do. 2024. Click-Gaussian: Interactive Segmentation to Any 3D Gaussians. arXiv preprint arXiv:2407.11793 (2024)

    work page arXiv 2024

  31. [31]

    Jorge Condor, Sebastien Speierer, Lukas Bode, Aljaz Bozic, Simon Green, Piotr Didyk, and Adrian Jarabo. 2025. Don’t Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media. ACM Trans. Graph. (2025)

    work page 2025

  32. [32]

    Daniel Cudeiro, Timo Bolkart, Cassidy Laidlaw, Anurag Ranjan, and Michael J Black. 2019. Capture, learning, and synthesis of 3D speaking styles. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 10101–10111

    work page 2019

  33. [33]

    Hiba Dahmani, Moussab Bennehar, Nathan Piasco, Luis Roldao, and Dzmitry Tsishkou. 2024. SWAG: Splatting in the Wild images with Appearance- conditioned Gaussians. arXiv preprint arXiv:2403.10427 (2024)

    work page arXiv 2024

  34. [34]

    Angela Dai, Angel X Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, and Matthias Nießner. 2017. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 5828–5839

    work page 2017

  35. [35]

    Anurag Dalal, Daniel Hagen, Kjell G Robbersmyr, and Kristian Muri Knausgård. 2024. Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Review. IEEE Access (2024)

    work page 2024

  36. [36]

    Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, and Jan Eric Lenssen. 2024. Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  37. [37]

    Matt Deitke, Dustin Schwenk, Jordi Salvador, Luca Weihs, Oscar Michel, Eli VanderBilt, Ludwig Schmidt, Kiana Ehsani, Aniruddha Kembhavi, and Ali Farhadi. 2023. Objaverse: A universe of annotated 3d objects. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 13142–13153

    work page 2023

  38. [38]

    Tianchen Deng, Yaohui Chen, Leyan Zhang, Jianfei Yang, Shenghai Yuan, Danwei Wang, and Weidong Chen. 2024. Compact 3d gaussian splatting for dense visual slam. arXiv preprint arXiv:2403.11247 (2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  39. [39]

    Helisa Dhamo, Yinyu Nie, Arthur Moreau, Jifei Song, Richard Shaw, Yiren Zhou, and Eduardo Pérez-Pellitero. 2023. HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting. arXiv preprint arXiv:2312.02902 (2023)

    work page arXiv 2023

  40. [40]

    Bin Dou, Tianyu Zhang, Yongjia Ma, Zhaohui Wang, and Zejian Yuan. 2024. CoSSegGaussians: Compact and Swift Scene Segmenting 3D Gaussians. arXiv preprint arXiv:2401.05925 (2024)

    work page arXiv 2024

  41. [41]

    Yuanxing Duan, Fangyin Wei, Qiyu Dai, Yuhang He, Wenzheng Chen, and Baoquan Chen. 2024. 4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes. In Proc. ACM Spec. Interest Group Comput. Graph. Interact. Tech. 1–11

    work page 2024

  42. [42]

    Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, and Zhangyang Wang. 2023. LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS. arXiv preprint arXiv:2311.17245 (2023)

    work page arXiv 2023

  43. [43]

    Guangchi Fang and Bing Wang. 2024. Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians.arXiv preprint arXiv:2403.14166 (2024)

    work page arXiv 2024

  44. [44]

    Jiemin Fang, Junjie Wang, Xiaopeng Zhang, Lingxi Xie, and Qi Tian. 2024. Gaussianeditor: Editing 3d gaussians delicately with text instructions. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  45. [45]

    Jiemin Fang, Taoran Yi, Xinggang Wang, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Matthias Nießner, and Qi Tian. 2022. Fast dynamic radiance fields with time-aware neural voxels. In SIGGRAPH Asia. 1–9

    work page 2022

  46. [46]

    Ben Fei, Jingyi Xu, Rui Zhang, Qingyuan Zhou, Weidong Yang, and Ying He. 2024. 3d gaussian splatting as new era: A survey. IEEE Trans. Vis. Comput. Graph. (2024)

    work page 2024

  47. [47]

    Qijun Feng, Zhen Xing, Zuxuan Wu, and Yu-Gang Jiang. 2024. FDGaussian: Fast Gaussian Splatting from Single Image via Geometric-aware Diffusion Model. arXiv preprint arXiv:2403.10242 (2024)

    work page arXiv 2024

  48. [48]

    Yutao Feng, Xiang Feng, Yintong Shang, Ying Jiang, Chang Yu, Zeshun Zong, Tianjia Shao, Hongzhi Wu, Kun Zhou, Chenfanfu Jiang, et al. 2024. Gaussian Splashing: Dynamic Fluid Synthesis with Gaussian Splatting. arXiv preprint arXiv:2401.15318 (2024)

    work page arXiv 2024

  49. [49]

    Sara Fridovich-Keil, Giacomo Meanti, Frederik Rahbæk Warburg, Benjamin Recht, and Angjoo Kanazawa. 2023. K-planes: Explicit radiance fields in space, time, and appearance. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 12479–12488

    work page 2023

  50. [50]

    Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A Efros, and Xiaolong Wang. 2024. COLMAP-Free 3D Gaussian Splatting. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  51. [51]

    Jian Gao, Chun Gu, Youtian Lin, Hao Zhu, Xun Cao, Li Zhang, and Yao Yao. 2023. Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing. arXiv preprint arXiv:2311.16043 (2023)

    work page arXiv 2023

  52. [52]

    Stephan J Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, and Julien Valentin. 2021. Fastnerf: High-fidelity neural rendering at 200fps. In Proc. IEEE Int. Conf. Comput. Vis. 14346–14355

    work page 2021

  53. [53]

    Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for autonomous driving? the kitti vision benchmark suite. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 3354–3361

    work page 2012

  54. [54]

    Chen Geng, Sida Peng, Zhen Xu, Hujun Bao, and Xiaowei Zhou. 2023. Learning neural volumetric representations of dynamic humans in minutes. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 8759–8770

    work page 2023

  55. [55]

    Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe, and Steven M Seitz. 2007. Multi-view stereo for community photo collections. In Proc. IEEE Int. Conf. Comput. Vis. 1–8

    work page 2007

  56. [56]

    Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2020. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144. Manuscript submitted to ACM 26 Guikun Chen and Wenguan Wang

    work page 2020

  57. [57]

    Steven J Gortler, Radek Grzeszczuk, Richard Szeliski, and Michael F Cohen. 2023. The lumigraph. InSeminal Graphics Papers: Pushing the Boundaries, Volume 2. 453–464

    work page 2023

  58. [58]

    Jeffrey P Grossman and William J Dally. 1998. Point sample rendering. In Render. Tech. 181–192

    work page 1998

  59. [59]

    Qiao Gu, Zhaoyang Lv, Duncan Frost, Simon Green, Julian Straub, and Chris Sweeney. 2024. EgoLifter: Open-world 3D Segmentation for Egocentric Perception. arXiv preprint arXiv:2403.18118 (2024)

    work page arXiv 2024

  60. [60]

    Antoine Guédon and Vincent Lepetit. 2024. SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  61. [61]

    Xiang Guo, Jiadai Sun, Yuchao Dai, Guanying Chen, Xiaoqing Ye, Xiao Tan, Errui Ding, Yumeng Zhang, and Jingdong Wang. 2023. Forward flow for novel view synthesis of dynamic scenes. In Proc. IEEE Int. Conf. Comput. Vis. 16022–16033

    work page 2023

  62. [62]

    Zhiyang Guo, Wengang Zhou, Li Li, Min Wang, and Houqiang Li. 2024. Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction. arXiv preprint arXiv:2403.11447 (2024)

    work page arXiv 2024

  63. [63]

    Xian-Feng Han, Hamid Laga, and Mohammed Bennamoun. 2019. Image-based 3D object reconstruction: State-of-the-art and trends in the deep learning era. IEEE Trans. Pattern Anal. Mach. Intell. 43, 5 (2019), 1578–1604

    work page 2019

  64. [64]

    Xianglong He, Junyi Chen, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan, Wanli Ouyang, and Tong He. 2024. Gvgen: Text-to-3d generation with volumetric representation. In Proc. Eur. Conf. Comput. Vis

    work page 2024

  65. [65]

    Peter Hedman, Julien Philip, True Price, Jan-Michael Frahm, George Drettakis, and Gabriel Brostow. 2018. Deep blending for free-viewpoint image-based rendering. ACM Trans. Graph. 37, 6 (2018), 1–15

    work page 2018

  66. [66]

    Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In Proc. Adv. Neural Inf. Process. Syst. 6840–6851

    work page 2020

  67. [67]

    Sheng Hong, Junjie He, Xinhu Zheng, Hesheng Wang, Hao Fang, Kangcheng Liu, Chunran Zheng, and Shaojie Shen. 2024. LIV-GaussMap: LiDAR-Inertial-Visual Fusion for Real-time 3D Radiance Field Map Rendering. arXiv preprint arXiv:2401.14857 (2024)

    work page arXiv 2024

  68. [68]

    Jiarui Hu, Xianhao Chen, Boyin Feng, Guanglin Li, Liangjing Yang, Hujun Bao, Guofeng Zhang, and Zhaopeng Cui. 2024. CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field. arXiv preprint arXiv:2403.16095 (2024)

    work page arXiv 2024

  69. [69]

    Liangxiao Hu, Hongwen Zhang, Yuxiang Zhang, Boyao Zhou, Boning Liu, Shengping Zhang, and Liqiang Nie. 2024. GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  70. [70]

    Shoukang Hu and Ziwei Liu. 2024. GauHuman: Articulated Gaussian Splatting from Monocular Human Videos. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  71. [71]

    Xu Hu, Yuxi Wang, Lue Fan, Junsong Fan, Junran Peng, Zhen Lei, Qing Li, and Zhaoxiang Zhang. 2024. Semantic Anything in 3D Gaussians. arXiv preprint arXiv:2401.17857 (2024)

    work page arXiv 2024

  72. [72]

    Yuanming Hu, Yu Fang, Ziheng Ge, Ziyin Qu, Yixin Zhu, Andre Pradhana, and Chenfanfu Jiang. 2018. A moving least squares material point method with displacement discontinuity and two-way rigid body coupling. ACM Trans. Graph. 37, 4 (2018), 1–14

    work page 2018

  73. [73]

    Huajian Huang, Longwei Li, Hui Cheng, and Sai-Kit Yeung. 2024. Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Cameras. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  74. [74]

    Jiajun Huang and Hongchuan Yu. 2023. Point’n Move: Interactive Scene Object Manipulation on Gaussian Splatting Radiance Fields.arXiv preprint arXiv:2311.16737 (2023)

    work page arXiv 2023

  75. [75]

    Letian Huang, Jiayang Bai, Jie Guo, and Yanwen Guo. 2024. GS++: Error Analyzing and Optimal Gaussian Splatting. arXiv preprint arXiv:2402.00752 (2024)

    work page arXiv 2024

  76. [76]

    Tianyu Huang, Yihan Zeng, Hui Li, Wangmeng Zuo, and Rynson WH Lau. 2025. DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians with Video Diffusion Priors. In Proc. AAAI Conf. Artif. Intell

    work page 2025

  77. [77]

    Yiming Huang, Beilei Cui, Long Bai, Ziqi Guo, Mengya Xu, and Hongliang Ren. 2024. Endo-4DGS: Distilling Depth Ranking for Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting. In Proc. Int. Conf. Med. Image Comput. Comput. Assist. Interv

    work page 2024

  78. [78]

    Yi-Hua Huang, Yang-Tian Sun, Ziyi Yang, Xiaoyang Lyu, Yan-Pei Cao, and Xiaojuan Qi. 2024. SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit

    work page 2024

  79. [79]

    Stephen James, Zicong Ma, David Rovick Arrojo, and Andrew J Davison. 2020. Rlbench: The robot learning benchmark & learning environment. IEEE Robotics and Automation Letters 5, 2 (2020), 3019–3026

    work page 2020

  80. [80]

    Rohit Jena, Ganesh Subramanian Iyer, Siddharth Choudhary, Brandon Smith, Pratik Chaudhari, and James Gee. 2023. SplatArmor: Articulated Gaussian splatting for animatable humans from monocular RGB videos. arXiv preprint arXiv:2311.10812 (2023)

    work page arXiv 2023

Showing first 80 references.