pith. sign in

arxiv: 2511.23292 · v3 · submitted 2025-11-28 · 💻 cs.CV · cs.GR

FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting

Tianhao Xie , Linlian Jiang , Xinxin Zuo , Yang Wang , Tiberiu Popa This is my paper

Pith reviewed 2026-05-17 04:38 UTC · model grok-4.3

classification 💻 cs.CV cs.GR
keywords Gaussian SplattingTexture ReparameterizationDeformation FieldAdaptive SamplingFrequency AlignmentReal-time Rendering2D GaussiansVisual Complexity
0
0 comments X

The pith

FACT-GS replaces uniform texture grids in 2D Gaussian Splatting with a learnable deformation field that allocates sampling density according to local visual frequency.

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

The paper shows how to improve texture efficiency inside each Gaussian primitive by tying sampling density to actual scene complexity instead of spreading it evenly. Standard per-Gaussian textures waste resolution on flat regions while under-sampling detailed ones, even when the total parameter count stays fixed. FACT-GS turns the parameterization into an optimization problem that learns a deformation field; the field's Jacobian then stretches or compresses the sampling grid locally so that high-frequency content receives more samples. Because the change is differentiable and keeps the underlying texture resolution constant, real-time rendering speed is unchanged. The result is sharper recovery of fine details in complex areas without increasing memory or compute.

Core claim

FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget.

What carries the argument

A deformation field whose Jacobian modulates local sampling density, reallocating fixed texture samples toward regions of higher visual frequency.

If this is right

  • High-frequency scene content receives denser sampling without raising total texture parameters.
  • Real-time rendering speed remains unchanged because the texture grid resolution is fixed.
  • Texture space is used more efficiently across primitives with varying visual complexity.
  • The approach stays compatible with existing 2D Gaussian Splatting pipelines.

Where Pith is reading between the lines

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

  • The same Jacobian-based density modulation could be tested on 3D Gaussian primitives or other splatting variants to check whether the frequency alignment benefit scales beyond 2D.
  • If the deformation field generalizes, it might reduce the need for multi-resolution texture pyramids in future real-time renderers.
  • The method opens a path to integrate local frequency estimation directly into the optimization loop rather than as a separate preprocessing step.

Load-bearing premise

The learned deformation field can be optimized so its Jacobian aligns sampling density with true visual frequency without causing instability, aliasing, or visible artifacts at the original parameter budget.

What would settle it

Side-by-side rendering of the same scene with equal texture resolution and parameter count, checking whether high-frequency edges and textures appear measurably sharper or less aliased under the new allocation than under uniform grids.

Figures

Figures reproduced from arXiv: 2511.23292 by Linlian Jiang, Tianhao Xie, Tiberiu Popa, Xinxin Zuo, Yang Wang.

Figure 1
Figure 1. Figure 1: Existing methods for novel view synthesis, such as 2DGS [ [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Method comparison of Textured GS and FACT-GS. (A) For the [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Novel view synthesis comparison under reduced primitive budgets (10% / 1% of default 2DGS). 2DGS [ [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 6
Figure 6. Figure 6: Ablation on the number of per-Gaussian texture parame [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison under high primitive budgets [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Per-Gaussian average RGB gradient magnitude. Tex [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
read the original abstract

Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent advances introduced per-primitive textures that incorporate spatial color variations within each Gaussian, improving their expressiveness. However, texture-based Gaussians parameterize appearance with a uniform per-Gaussian sampling grid, allocating equal sampling density regardless of local visual complexity, which leads to inefficient texture space utilization. We introduce FACT-GS, a Frequency-Aligned Complexity-aware Texture Gaussian Splatting framework that allocates texture sampling density according to local visual frequency. Grounded in adaptive sampling theory, FACT-GS reformulates texture parameterization as a differentiable sampling-density allocation problem, replacing the uniform textures with a learnable frequency-aware allocation strategy implemented via a deformation field whose Jacobian modulates local sampling density. Built on 2D Gaussian Splatting, FACT-GS performs non-uniform sampling on fixed-resolution texture grids, preserving real-time performance while recovering sharper high-frequency details under the same parameter budget.

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

2 major / 1 minor

Summary. The paper introduces FACT-GS, a Frequency-Aligned Complexity-Aware Texture Gaussian Splatting framework built on 2D Gaussian Splatting. It claims to reformulate per-Gaussian texture parameterization as a differentiable sampling-density allocation problem, replacing uniform sampling grids with a learnable frequency-aware strategy implemented via a deformation field whose Jacobian modulates local sampling density. This is intended to allocate higher sampling density to high-frequency regions, recovering sharper details under a fixed parameter budget while preserving real-time rendering performance.

Significance. If the central mechanism holds, the work could improve texture utilization efficiency in Gaussian Splatting without sacrificing speed, offering a grounded approach from adaptive sampling theory to better handle visual complexity. The explicit focus on maintaining real-time performance under the same budget is a practical strength.

major comments (2)
  1. [Abstract] Abstract: The reformulation relies on a learnable deformation field whose Jacobian modulates local sampling density, but no equations, parameterization details, or integration steps into the 2DGS pipeline are provided. This absence prevents verification of how frequency alignment is achieved or how the modulation interacts with the fixed-resolution texture grid.
  2. [Abstract] Abstract: The description states that the Jacobian modulates sampling density in a frequency-aware manner, yet provides no indication of regularization, projection, or constraints to enforce Jacobian determinant > 0 everywhere. Without such terms, gradient descent risks producing folds, negative densities, or aliasing artifacts that would directly contradict the claim of improved high-frequency recovery without visible degradation.
minor comments (1)
  1. [Abstract] The abstract could be strengthened by briefly noting the specific loss terms or optimization schedule used to train the deformation field.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our work. We address each major comment point by point below, clarifying the technical details and making targeted revisions to improve the presentation of the method.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The reformulation relies on a learnable deformation field whose Jacobian modulates local sampling density, but no equations, parameterization details, or integration steps into the 2DGS pipeline are provided. This absence prevents verification of how frequency alignment is achieved or how the modulation interacts with the fixed-resolution texture grid.

    Authors: We agree that the abstract, being a high-level summary, does not include the full equations. The complete parameterization of the deformation field, the Jacobian-based density modulation, frequency alignment mechanism, and integration steps with the 2D Gaussian Splatting pipeline are provided in Section 3.2 (Equations 3-6) and Section 3.3 of the manuscript. To address the verification concern directly, we have revised the abstract to include a concise reference to the core formulation and key equation. revision: yes

  2. Referee: [Abstract] Abstract: The description states that the Jacobian modulates sampling density in a frequency-aware manner, yet provides no indication of regularization, projection, or constraints to enforce Jacobian determinant > 0 everywhere. Without such terms, gradient descent risks producing folds, negative densities, or aliasing artifacts that would directly contradict the claim of improved high-frequency recovery without visible degradation.

    Authors: This is a valid concern regarding numerical stability. The manuscript includes a regularization term in the total loss (Section 4.2, Equation 10) that penalizes negative Jacobian determinants to prevent folding and ensure positive local densities. We also apply a soft projection during optimization to maintain invertibility. We have expanded the method section with an explicit paragraph on these safeguards and added an ablation study quantifying their impact on artifact reduction. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation introduces independent learnable component.

full rationale

The paper's central construction replaces uniform texture grids with a new learnable deformation field whose Jacobian is used to modulate sampling density in a frequency-aware way. This is presented as an explicit reformulation grounded in adaptive sampling theory, adding a differentiable component rather than re-expressing a prior fitted quantity, renaming a known result, or reducing via self-citation to an unverified premise. The abstract and description contain no equations or steps that equate the output allocation directly to the input by construction, and the method is described as preserving real-time performance under the same parameter budget without invoking load-bearing self-references.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The approach rests on adaptive sampling theory and the assumption that a deformation field can be trained to match visual frequency; no explicit free parameters or new physical entities are named.

axioms (1)
  • domain assumption Adaptive sampling theory justifies allocating density according to local visual frequency
    Abstract states the method is grounded in adaptive sampling theory.
invented entities (1)
  • learnable deformation field whose Jacobian modulates sampling density no independent evidence
    purpose: To replace uniform texture grids with frequency-aware non-uniform sampling
    New component introduced to implement the allocation strategy

pith-pipeline@v0.9.0 · 5483 in / 1237 out tokens · 32430 ms · 2026-05-17T04:38:19.461356+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

52 extracted references · 52 canonical work pages · 1 internal anchor

  1. [1]

    Building rome in a day.Communications of the ACM, 54 (10):105–112, 2011

    Sameer Agarwal, Yasutaka Furukawa, Noah Snavely, Ian Si- mon, Brian Curless, Steven M Seitz, and Richard Szeliski. Building rome in a day.Communications of the ACM, 54 (10):105–112, 2011. 2

    work page 2011

  2. [2]

    Mip-nerf: A multiscale representation for anti-aliasing neu- ral radiance fields

    Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. Mip-nerf: A multiscale representation for anti-aliasing neu- ral radiance fields. InProceedings of the IEEE/CVF inter- national conference on computer vision, pages 5855–5864,

    work page

  3. [3]

    Mip-nerf 360: Unbounded anti-aliased neural radiance fields

    Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5470–5479, 2022. 2, 6, 7

    work page 2022

  4. [4]

    Textured gaussians for en- hanced 3d scene appearance modeling

    Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, Jia-Bin Huang, Johannes Kopf, Gordon Wetzstein, et al. Textured gaussians for en- hanced 3d scene appearance modeling. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 8964–8974, 2025. 1, 2, 3, 5, 6, 7, 8

    work page 2025

  5. [5]

    Image quality mea- sures and their performance.IEEE Transactions on commu- nications, 43(12):2959–2965, 2002

    Ahmet M Eskicioglu and Paul S Fisher. Image quality mea- sures and their performance.IEEE Transactions on commu- nications, 43(12):2959–2965, 2002. 4, 5, 8

    work page 2002

  6. [6]

    Flashgs: Efficient 3d gaussian splatting for large-scale and high-resolution rendering

    Guofeng Feng, Siyan Chen, Rong Fu, Zimu Liao, Yi Wang, Tao Liu, Boni Hu, Linning Xu, Zhilin Pei, Hengjie Li, et al. Flashgs: Efficient 3d gaussian splatting for large-scale and high-resolution rendering. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 26652– 26662, 2025. 2

    work page 2025

  7. [7]

    Dy- namic 3d gaussian fields for urban areas.arXiv preprint arXiv:2406.03175, 2024

    Tobias Fischer, Jonas Kulhanek, Samuel Rota Bulo, Lorenzo Porzi, Marc Pollefeys, and Peter Kontschieder. Dy- namic 3d gaussian fields for urban areas.arXiv preprint arXiv:2406.03175, 2024. 2

    work page arXiv 2024

  8. [8]

    Colmap-free 3d gaussian splat- ting

    Yang Fu, Sifei Liu, Amey Kulkarni, Jan Kautz, Alexei A Efros, and Xiaolong Wang. Colmap-free 3d gaussian splat- ting. InProceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 20796–20805,

    work page

  9. [9]

    Accurate, dense, and robust multiview stereopsis.IEEE transactions on pattern analysis and machine intelligence, 32(8):1362–1376, 2009

    Yasutaka Furukawa and Jean Ponce. Accurate, dense, and robust multiview stereopsis.IEEE transactions on pattern analysis and machine intelligence, 32(8):1362–1376, 2009. 2

    work page 2009

  10. [10]

    Towards internet-scale multi-view stereo

    Yasutaka Furukawa, Brian Curless, Steven M Seitz, and Richard Szeliski. Towards internet-scale multi-view stereo. In2010 IEEE computer society conference on computer vi- sion and pattern recognition, pages 1434–1441. IEEE, 2010. 2

    work page 2010

  11. [11]

    Multidimensional adap- tive sampling and reconstruction for ray tracing

    Toshiya Hachisuka, Wojciech Jarosz, Richard Peter Weistroffer, Kevin Dale, Greg Humphreys, Matthias Zwicker, and Henrik Wann Jensen. Multidimensional adap- tive sampling and reconstruction for ray tracing. InACM SIGGRAPH 2008 papers, pages 1–10. 2008. 2, 3

    work page 2008

  12. [12]

    Fundamentals of texture mapping and im- age warping

    Paul S Heckbert. Fundamentals of texture mapping and im- age warping. 1989. 2

    work page 1989

  13. [13]

    Survey of texture mapping.IEEE computer graphics and applications, 6(11):56–67, 2007

    Paul S Heckbert. Survey of texture mapping.IEEE computer graphics and applications, 6(11):56–67, 2007. 3

    work page 2007

  14. [14]

    2d gaussian splatting for geometrically ac- curate radiance fields

    Binbin Huang, Zehao Yu, Anpei Chen, Andreas Geiger, and Shenghua Gao. 2d gaussian splatting for geometrically ac- curate radiance fields. InACM SIGGRAPH 2024 conference papers, pages 1–11, 2024. 1, 2, 3, 6, 7, 8

    work page 2024

  15. [15]

    Textured-gs: Gaus- sian splatting with spatially defined color and opacity.arXiv preprint arXiv:2407.09733, 2024

    Zhentao Huang and Minglun Gong. Textured-gs: Gaus- sian splatting with spatially defined color and opacity.arXiv preprint arXiv:2407.09733, 2024. 2, 3, 7, 8

    work page arXiv 2024

  16. [16]

    Large scale multi-view stereopsis eval- uation

    Rasmus Jensen, Anders Dahl, George V ogiatzis, Engin Tola, and Henrik Aanæs. Large scale multi-view stereopsis eval- uation. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 406–413, 2014. 6, 7

    work page 2014

  17. [17]

    3d gaussian splatting for real-time radiance field rendering.ACM Trans

    Bernhard Kerbl, Georgios Kopanas, Thomas Leimk ¨uhler, and George Drettakis. 3d gaussian splatting for real-time radiance field rendering.ACM Trans. Graph., 42(4):139–1,

    work page

  18. [18]

    Tanks and temples: Benchmarking large-scale scene reconstruction.ACM Transactions on Graphics (ToG), 36 (4):1–13, 2017

    Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. Tanks and temples: Benchmarking large-scale scene reconstruction.ACM Transactions on Graphics (ToG), 36 (4):1–13, 2017. 6, 7

    work page 2017

  19. [19]

    Wildgaussians: 3d gaussian splatting in the wild,

    Jonas Kulhanek, Songyou Peng, Zuzana Kukelova, Marc Pollefeys, and Torsten Sattler. Wildgaussians: 3d gaussian splatting in the wild.arXiv preprint arXiv:2407.08447, 2024. 2

    work page arXiv 2024

  20. [20]

    Mosca: Dynamic gaussian fusion from casual videos via 4d motion scaffolds

    Jiahui Lei, Yijia Weng, Adam W Harley, Leonidas Guibas, and Kostas Daniilidis. Mosca: Dynamic gaussian fusion from casual videos via 4d motion scaffolds. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 6165–6177, 2025. 3

    work page 2025

  21. [21]

    3d-hgs: 3d half-gaussian splatting

    Haolin Li, Jinyang Liu, Mario Sznaier, and Octavia Camps. 3d-hgs: 3d half-gaussian splatting. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 10996–11005, 2025. 3 9

    work page 2025

  22. [22]

    Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normaliza- tion

    Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, and Lin Gu. Dngaussian: Optimizing sparse-view 3d gaussian radiance fields with global-local depth normaliza- tion. InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 20775–20785,

    work page

  23. [23]

    Vastgaussian: Vast 3d gaussians for large scene reconstruction

    Jiaqi Lin, Zhihao Li, Xiao Tang, Jianzhuang Liu, Shiyong Liu, Jiayue Liu, Yangdi Lu, Xiaofei Wu, Songcen Xu, You- liang Yan, et al. Vastgaussian: Vast 3d gaussians for large scene reconstruction. InProceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition, pages 5166–5175, 2024. 2

    work page 2024

  24. [24]

    3dgs-enhancer: Enhancing unbounded 3d gaussian splatting with view- consistent 2d diffusion priors.Advances in Neural Informa- tion Processing Systems, 37:133305–133327, 2024

    Xi Liu, Chaoyi Zhou, and Siyu Huang. 3dgs-enhancer: Enhancing unbounded 3d gaussian splatting with view- consistent 2d diffusion priors.Advances in Neural Informa- tion Processing Systems, 37:133305–133327, 2024. 3

    work page 2024

  25. [25]

    Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar

    Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar. Local light field fusion: Practical view syn- thesis with prescriptive sampling guidelines.ACM Transac- tions on Graphics (TOG), 2019. 6, 7

    work page 2019

  26. [26]

    Nerf: Representing scenes as neural radiance fields for view syn- thesis.Communications of the ACM, 65(1):99–106, 2021

    Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view syn- thesis.Communications of the ACM, 65(1):99–106, 2021. 2, 6, 7

    work page 2021

  27. [27]

    Filtering after shading with stochastic texture fil- tering.Proceedings of the ACM on Computer Graphics and Interactive Techniques, 7(1):1–20, 2024

    Matt Pharr, Bartlomiej Wronski, Marco Salvi, and Marcos Fajardo. Filtering after shading with stochastic texture fil- tering.Proceedings of the ACM on Computer Graphics and Interactive Techniques, 7(1):1–20, 2024. 3

    work page 2024

  28. [28]

    Gstex: Per-primitive tex- turing of 2d gaussian splatting for decoupled appearance and geometry modeling

    Victor Rong, Jingxiang Chen, Sherwin Bahmani, Kiriakos N Kutulakos, and David B Lindell. Gstex: Per-primitive tex- turing of 2d gaussian splatting for decoupled appearance and geometry modeling. In2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 3508–

    work page

  29. [29]

    2, 3, 5, 7

    IEEE, 2025. 2, 3, 5, 7

    work page 2025

  30. [30]

    Adaptive sampling and reconstruction using greedy error minimization.ACM Transactions on Graphics (TOG), 30 (6):1–12, 2011

    Fabrice Rousselle, Claude Knaus, and Matthias Zwicker. Adaptive sampling and reconstruction using greedy error minimization.ACM Transactions on Graphics (TOG), 30 (6):1–12, 2011. 2, 3, 4

    work page 2011

  31. [31]

    Texture mapping progressive meshes

    Pedro V Sander, John Snyder, Steven J Gortler, and Hugues Hoppe. Texture mapping progressive meshes. InProceed- ings of the 28th annual conference on Computer graphics and interactive techniques, pages 409–416, 2001. 2, 4

    work page 2001

  32. [32]

    Structure- from-motion revisited

    Johannes L Schonberger and Jan-Michael Frahm. Structure- from-motion revisited. InProceedings of the IEEE con- ference on computer vision and pattern recognition, pages 4104–4113, 2016. 2

    work page 2016

  33. [33]

    A comparison and eval- uation of multi-view stereo reconstruction algorithms

    Steven M Seitz, Brian Curless, James Diebel, Daniel Scharstein, and Richard Szeliski. A comparison and eval- uation of multi-view stereo reconstruction algorithms. In 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), pages 519–528. IEEE, 2006

    work page 2006

  34. [34]

    Photo tourism: exploring photo collections in 3d

    Noah Snavely, Steven M Seitz, and Richard Szeliski. Photo tourism: exploring photo collections in 3d. InACM siggraph 2006 papers, pages 835–846. 2006

    work page 2006

  35. [35]

    Model- ing the world from internet photo collections.International journal of computer vision, 80(2):189–210, 2008

    Noah Snavely, Steven M Seitz, and Richard Szeliski. Model- ing the world from internet photo collections.International journal of computer vision, 80(2):189–210, 2008. 2

    work page 2008

  36. [36]

    Hdgs: Textured 2d gaussian splatting for enhanced scene rendering.arXiv preprint arXiv:2412.01823,

    Yunzhou Song, Heguang Lin, Jiahui Lei, Lingjie Liu, and Kostas Daniilidis. Hdgs: Textured 2d gaussian splatting for enhanced scene rendering.arXiv preprint arXiv:2412.01823,

    work page arXiv

  37. [37]

    Svg-ir: Spatially-varying gaussian splatting for in- verse rendering

    Hanxiao Sun, Yupeng Gao, Jin Xie, Jian Yang, and Beibei Wang. Svg-ir: Spatially-varying gaussian splatting for in- verse rendering. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 16143–16152, 2025. 3

    work page 2025

  38. [38]

    Neural brdf representation and importance sampling

    Alejandro Sztrajman, Gilles Rainer, Tobias Ritschel, and Tim Weyrich. Neural brdf representation and importance sampling. InComputer Graphics Forum, pages 332–346. Wiley Online Library, 2021. 2, 3

    work page 2021

  39. [39]

    Block-nerf: Scalable large scene neural view synthesis

    Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Prad- han, Ben Mildenhall, Pratul P Srinivasan, Jonathan T Barron, and Henrik Kretzschmar. Block-nerf: Scalable large scene neural view synthesis. InProceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, pages 8248–8258, 2022. 2

    work page 2022

  40. [40]

    Ref-nerf: Struc- tured view-dependent appearance for neural radiance fields

    Dor Verbin, Peter Hedman, Ben Mildenhall, Todd Zickler, Jonathan T Barron, and Pratul P Srinivasan. Ref-nerf: Struc- tured view-dependent appearance for neural radiance fields. In2022 IEEE/CVF Conference on Computer Vision and Pat- tern Recognition (CVPR), pages 5481–5490. IEEE, 2022. 2

    work page 2022

  41. [41]

    Efficiency of adaptive sampling in surface texture measurement for structured surfaces

    Jian Wang, Xiangqian Jiang, LA Blunt, Richard K Leach, and Paul J Scott. Efficiency of adaptive sampling in surface texture measurement for structured surfaces. InJournal of Physics: Conference Series, page 012017. IOP Publishing,

    work page

  42. [42]

    Pyramidal parametrics

    Lance Williams. Pyramidal parametrics. InProceedings of the 10th annual conference on Computer graphics and inter- active techniques, pages 1–11, 1983. 3

    work page 1983

  43. [43]

    Dynamic lidar re- simulation using compositional neural fields

    Hanfeng Wu, Xingxing Zuo, Stefan Leutenegger, Or Litany, Konrad Schindler, and Shengyu Huang. Dynamic lidar re- simulation using compositional neural fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 19988–19998, 2024. 2

    work page 2024

  44. [44]

    SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors

    Rui Xu, Wenyue Chen, Jiepeng Wang, Yuan Liu, Peng Wang, Lin Gao, Shiqing Xin, Taku Komura, Xin Li, and Wenping Wang. Supergaussians: Enhancing gaussian splat- ting using primitives with spatially varying colors.arXiv preprint arXiv:2411.18966, 2024. 3, 7

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  45. [45]

    Texture-gs: Disentangling the geometry and texture for 3d gaussian splatting editing

    Tian-Xing Xu, Wenbo Hu, Yu-Kun Lai, Ying Shan, and Song-Hai Zhang. Texture-gs: Disentangling the geometry and texture for 3d gaussian splatting editing. InEuropean Conference on Computer Vision, pages 37–53. Springer,

    work page

  46. [46]

    gsplat: An open-source library for gaussian splatting.Journal of Machine Learning Research, 26(34):1–17, 2025

    Vickie Ye, Ruilong Li, Justin Kerr, Matias Turkulainen, Brent Yi, Zhuoyang Pan, Otto Seiskari, Jianbo Ye, Jeffrey Hu, Matthew Tancik, et al. gsplat: An open-source library for gaussian splatting.Journal of Machine Learning Research, 26(34):1–17, 2025. 6

    work page 2025

  47. [47]

    Mip-splatting: Alias-free 3d gaussian splat- 10 ting

    Zehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler, and Andreas Geiger. Mip-splatting: Alias-free 3d gaussian splat- 10 ting. InProceedings of the IEEE/CVF conference on com- puter vision and pattern recognition, pages 19447–19456,

    work page

  48. [48]

    The unreasonable effectiveness of deep features as a perceptual metric

    Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shecht- man, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 586–595, 2018. 6

    work page 2018

  49. [49]

    Neural shell texture splatting: More details and fewer primitives

    Xin Zhang, Anpei Chen, Jincheng Xiong, Pinxuan Dai, Yu- jun Shen, and Weiwei Xu. Neural shell texture splatting: More details and fewer primitives. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 25229–25238, 2025. 2, 3, 7

    work page 2025

  50. [50]

    Instant-nerf: In- stant on-device neural radiance field training via algorithm- accelerator co-designed near-memory processing

    Yang Katie Zhao, Shang Wu, Jingqun Zhang, Sixu Li, Chaojian Li, and Yingyan Celine Lin. Instant-nerf: In- stant on-device neural radiance field training via algorithm- accelerator co-designed near-memory processing. In2023 60th ACM/IEEE Design Automation Conference (DAC), pages 1–6. IEEE, 2023. 2

    work page 2023

  51. [51]

    Fsgs: Real-time few-shot view synthesis using gaussian splatting

    Zehao Zhu, Zhiwen Fan, Yifan Jiang, and Zhangyang Wang. Fsgs: Real-time few-shot view synthesis using gaussian splatting. InEuropean conference on computer vision, pages 145–163. Springer, 2024. 3

    work page 2024

  52. [52]

    Recent advances in adaptive sampling and reconstruction for monte carlo ren- dering

    Matthias Zwicker, Wojciech Jarosz, Jaakko Lehtinen, Bochang Moon, Ravi Ramamoorthi, Fabrice Rousselle, Pradeep Sen, Cyril Soler, and S-E Yoon. Recent advances in adaptive sampling and reconstruction for monte carlo ren- dering. InComputer graphics forum, pages 667–681. Wiley Online Library, 2015. 2, 3, 4 11

    work page 2015