pith. sign in

arxiv: 2210.00379 · v8 · pith:3K5THX67new · submitted 2022-10-01 · 💻 cs.CV

NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)

Kyle Gao , Yina Gao , Hongjie He , Dening Lu , Linlin Xu , Jonathan Li This is my paper

Pith reviewed 2026-05-24 10:30 UTC · model grok-4.3

classification 💻 cs.CV
keywords NeRFNeural Radiance FieldsNovel View Synthesis3D VisionGaussian SplattingNeural FieldsImplicit RepresentationsSurvey
0
0 comments X

The pith

This survey organizes five years of NeRF research into taxonomies and benchmarks its performance against later methods.

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

The paper establishes a structured overview of Neural Radiance Field techniques developed between 2020 and 2025. It separates work from the period when NeRF led novel view synthesis from the later period when implicit and hybrid neural fields occupied narrower roles after Gaussian Splatting appeared. The review supplies an explanation of NeRF theory and differentiable volume rendering, supplies architecture and application taxonomies, reports speed and quality benchmarks, and lists key datasets. A reader would use it to trace how the field adapted once a faster explicit alternative emerged.

Core claim

We present a comprehensive survey of NeRF papers from the past five years (2020-2025). These include papers from the pre-Gaussian Splatting era, where NeRF dominated the field for novel view synthesis and 3D implicit and hybrid representation neural field learning. We also include works from the post-Gaussian Splatting era where NeRF and implicit/hybrid neural fields found more niche applications. Our survey is organized into architecture and application-based taxonomies in the pre-Gaussian Splatting era, as well as a categorization of active research areas for NeRF, neural field, and implicit/hybrid neural representation methods. We provide an introduction to the theory of NeRF and its训练via

What carries the argument

Architecture-based and application-based taxonomies that group NeRF, implicit, and hybrid neural representation methods across pre- and post-Gaussian Splatting periods.

If this is right

  • The taxonomies allow researchers to locate gaps in current NeRF applications.
  • Benchmark tables enable direct speed and quality comparisons between classical NeRF and later implicit or hybrid models.
  • The theory section supplies a starting point for readers new to differentiable volume rendering.
  • Categorization of active research areas indicates which neural-field directions remain viable after Gaussian Splatting.

Where Pith is reading between the lines

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

  • The niche-application focus after 2023 suggests NeRF methods may persist mainly in settings where explicit splatting is impractical.
  • A future extension could add quantitative meta-analysis of how often NeRF papers cite or are cited by Gaussian-Splatting work.
  • The survey structure could serve as a template for tracking other representation shifts in 3D vision.

Load-bearing premise

The papers selected and the taxonomies proposed cover the literature representatively without major omissions or systematic bias.

What would settle it

Discovery of multiple prominent NeRF papers published 2020-2025 that fall outside the stated taxonomies or are absent from the survey entirely.

Figures

Figures reproduced from arXiv: 2210.00379 by Dening Lu, Hongjie He, Jonathan Li, Kyle Gao, Linlin Xu, Yina Gao.

Figure 1
Figure 1. Figure 1: The NeRF volume rendering and training process. Image sourced from [1]. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Diagram of the Integrated Positional Encoding (IPE) of mip-NeRF (Figure 1 in [46]). a) Standard ray-based point sampled of NeRF; b) Cone-sampling [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Taxonomy of selected key NeRF innovation papers. The papers are selected using a combination of citations and GitHub star rating. We note that [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Ref-NeRF results in the ”garden spheres” scene of [38], showings its [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Example of a hybrid representation scene representation method, the Instant-NGP [42]. During training, the scene information is stored in both the [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Magic3D: Example two-stage text-to-3D generation (Figure 1 in [83]). Left: low resolution text-to-3D using NeRF; middle and right: higher resolution [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: NeRFRen [24] is capable of accurately reconstructing the depth (and [PITH_FULL_IMAGE:figures/full_fig_p014_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Application of NeRF models. Papers are selected based on application as well as citation numbers and GitHub star rating. [PITH_FULL_IMAGE:figures/full_fig_p017_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: NeuS [167] surface reconstruction results on the BlendedMVS [188] [PITH_FULL_IMAGE:figures/full_fig_p019_9.png] view at source ↗
read the original abstract

In March 2020, Neural Radiance Field (NeRF) revolutionized Computer Vision, allowing for implicit, neural network-based scene representation and novel view synthesis. NeRF models have found diverse applications in robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, and more. In August 2023, Gaussian Splatting, a direct competitor to the NeRF-based framework, was proposed, gaining tremendous momentum and overtaking NeRF-based research in terms of interest as the dominant framework for novel view synthesis. We present a comprehensive survey of NeRF papers from the past five years (2020-2025). These include papers from the pre-Gaussian Splatting era, where NeRF dominated the field for novel view synthesis and 3D implicit and hybrid representation neural field learning. We also include works from the post-Gaussian Splatting era where NeRF and implicit/hybrid neural fields found more niche applications. Our survey is organized into architecture and application-based taxonomies in the pre-Gaussian Splatting era, as well as a categorization of active research areas for NeRF, neural field, and implicit/hybrid neural representation methods. We provide an introduction to the theory of NeRF and its training via differentiable volume rendering. We also present a benchmark comparison of the performance and speed of classical NeRF, implicit and hybrid neural representation, and neural field models, and an overview of key datasets.

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 manuscript claims to deliver a comprehensive survey of NeRF papers from 2020-2025, covering both the pre-Gaussian Splatting era (where NeRF dominated novel view synthesis and implicit/hybrid neural field learning) and the post-Gaussian Splatting era (where NeRF and related methods occupy niche applications). The survey is organized via architecture-based and application-based taxonomies for the earlier period plus a categorization of active research areas; it also supplies an introduction to NeRF theory and differentiable volume rendering, benchmark comparisons of performance and speed across classical NeRF, implicit, hybrid, and neural-field models, and an overview of key datasets. Applications in robotics, urban mapping, autonomous navigation, and VR/AR are highlighted.

Significance. If the taxonomies prove representative and the benchmark comparisons are reproducible and fairly constructed, the survey could serve as a practical reference that helps the community track NeRF's evolving role after Gaussian Splatting displaced it as the dominant novel-view-synthesis framework. The inclusion of speed/performance benchmarks and dataset summaries would add concrete utility beyond narrative organization.

major comments (2)
  1. [Abstract] Abstract: the central claim that the work constitutes a 'comprehensive survey' of NeRF papers (2020-2025) with 'architecture and application-based taxonomies' rests on the unstated assumption that the selected papers are representative. No search protocol, inclusion/exclusion criteria, database sources, total paper count, or coverage metric is supplied, rendering it impossible to verify whether the taxonomies systematically under-represent post-2023 hybrid methods or particular application domains.
  2. [Benchmark comparison] Benchmark comparison paragraph: the manuscript states that it 'present[s] a benchmark comparison of the performance and speed' of classical NeRF, implicit/hybrid, and neural-field models, yet provides neither the list of evaluated methods, the precise metrics, the datasets employed, nor any reference to a table or figure containing the quantitative results. This omission prevents assessment of whether the comparisons fairly support claims about NeRF's niche viability after Gaussian Splatting.
minor comments (1)
  1. [Abstract] The abstract would benefit from an explicit statement of the total number of papers reviewed to give readers an immediate sense of scope.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on the survey's claims of comprehensiveness and the benchmark section. We address each major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that the work constitutes a 'comprehensive survey' of NeRF papers (2020-2025) with 'architecture and application-based taxonomies' rests on the unstated assumption that the selected papers are representative. No search protocol, inclusion/exclusion criteria, database sources, total paper count, or coverage metric is supplied, rendering it impossible to verify whether the taxonomies systematically under-represent post-2023 hybrid methods or particular application domains.

    Authors: We agree that transparency in paper selection is required to support the 'comprehensive' claim. In the revised manuscript we will add a dedicated subsection in the introduction that specifies the literature search protocol, including databases (arXiv, Google Scholar, CVPR/ICCV/ECCV), keywords, time range (2020-2025), inclusion criteria (relevance to NeRF/neural fields/implicit representations), exclusion criteria, and the total number of papers reviewed and categorized. This will enable readers to evaluate coverage of post-2023 hybrids and application domains. revision: yes

  2. Referee: [Benchmark comparison] Benchmark comparison paragraph: the manuscript states that it 'present[s] a benchmark comparison of the performance and speed' of classical NeRF, implicit/hybrid, and neural-field models, yet provides neither the list of evaluated methods, the precise metrics, the datasets employed, nor any reference to a table or figure containing the quantitative results. This omission prevents assessment of whether the comparisons fairly support claims about NeRF's niche viability after Gaussian Splatting.

    Authors: The referee is correct that the current text announces a benchmark comparison without supplying the supporting details or table. We will revise the manuscript to include an explicit table (or subsection) listing the evaluated methods, metrics (PSNR, SSIM, rendering FPS), datasets used, and citations to the source papers or reported results. The table will distinguish literature-reported numbers from any new comparisons and will be referenced directly from the benchmark paragraph. revision: yes

Circularity Check

0 steps flagged

No circularity: descriptive survey without derivations or predictions

full rationale

This is a literature survey that organizes existing external papers into taxonomies and provides benchmark overviews; it contains no mathematical derivations, fitted parameters, predictions, or first-principles results that could reduce to the paper's own inputs by construction. The central claim of providing a representative taxonomy rests on selection of prior work rather than any self-referential equation or self-citation chain that defines its own output. No steps meet the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper the central claim rests only on the completeness and accuracy of its literature selection and taxonomy construction; no free parameters, axioms, or invented entities are introduced by the authors.

pith-pipeline@v0.9.0 · 5806 in / 1037 out tokens · 22047 ms · 2026-05-24T10:30:46.103177+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 7 Pith papers

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

  1. Motion-Enabled Tomography via Gaussian Mixture Models

    math.NA 2026-05 unverdicted novelty 7.0

    A parametric GMM model for motion-enabled tomography that decouples reconstruction into sub-problems and tests on 2D simulations of intersecting trajectories.

  2. Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes

    cs.CV 2026-05 unverdicted novelty 7.0

    S2C-3D reconstructs complete high-fidelity 3D scenes from as few as 6-8 images by finetuning a diffusion model on scene data, applying consistency-conditioned sampling, and planning trajectories for full coverage.

  3. MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene

    cs.CV 2026-04 unverdicted novelty 7.0

    MU-GeNeRF combines source-view and target-view uncertainties via a heteroscedastic loss to enable distractor-aware generalizable NeRF reconstruction that matches scene-specific methods.

  4. AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors

    cs.CV 2026-04 unverdicted novelty 7.0

    AnchorSplat uses anchor-aligned 3D Gaussians guided by geometric priors for feed-forward scene reconstruction, achieving SOTA novel view synthesis on ScanNet++ with fewer primitives and better view consistency.

  5. Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes

    cs.CV 2026-05 unverdicted novelty 6.0

    Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.

  6. 3D Reconstruction and Knowledge Distillation to Improve Multi-View Image Models to Explore Spike Volume Estimation in Wheat

    cs.CV 2026-05 unverdicted novelty 4.0

    Knowledge distillation from a rigid-invariant 3D point cloud network into a regulated multi-view Transformer yields lower-error, faster wheat spike volume estimates from 2D images.

  7. Safe Navigation using Neural Radiance Fields via Reachable Sets

    eess.SY 2026-04 unverdicted novelty 3.0

    Safe robot navigation in obstacle-rich environments is demonstrated in simulation by representing obstacles with NeRFs and enforcing safety via reachable-set constraints inside a linear-matrix-inequality optimal-contr...

Reference graph

Works this paper leans on

192 extracted references · 192 canonical work pages · cited by 7 Pith papers · 11 internal anchors

  1. [1]

    Nerf: Representing scenes as neural radiance fields for view synthesis,

    B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoor- thi, and R. Ng, “Nerf: Representing scenes as neural radiance fields for view synthesis,” inEuropean conference on computer vision. Springer, 2020, pp. 405–421

    work page 2020

  2. [2]

    Structure-from-motion revisited,

    J. L. Schonberger and J.-M. Frahm, “Structure-from-motion revisited,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4104–4113

    work page 2016

  3. [3]

    Light field rendering,

    M. Levoy and P. Hanrahan, “Light field rendering,” in Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, 1996, pp. 31–42

    work page 1996

  4. [4]

    The lumigraph,

    S. J. Gortler, R. Grzeszczuk, R. Szeliski, and M. F. Cohen, “The lumigraph,” in Proceedings of the 23rd annual conference on Computer graphics and interactive techniques , 1996, pp. 43–54

    work page 1996

  5. [5]

    Local light field fusion: Practical view synthesis with prescriptive sampling guidelines,

    B. Mildenhall, P. P. Srinivasan, R. Ortiz-Cayon, N. K. Kalantari, R. Ra- mamoorthi, R. Ng, and A. Kar, “Local light field fusion: Practical view synthesis with prescriptive sampling guidelines,” ACM Transactions on Graphics (TOG), vol. 38, no. 4, pp. 1–14, 2019

    work page 2019

  6. [6]

    Scene representation networks: Continuous 3d-structure-aware neural scene representations,

    V . Sitzmann, M. Zollh ¨ofer, and G. Wetzstein, “Scene representation networks: Continuous 3d-structure-aware neural scene representations,” Advances in Neural Information Processing Systems , vol. 32, 2019

    work page 2019

  7. [7]

    Neural volumes: learning dynamic renderable volumes from images,

    S. Lombardi, T. Simon, J. Saragih, G. Schwartz, A. Lehrmann, and Y . Sheikh, “Neural volumes: learning dynamic renderable volumes from images,” ACM Transactions on Graphics (TOG) , vol. 38, no. 4, pp. 1–14, 2019

    work page 2019

  8. [8]

    Differ- entiable volumetric rendering: Learning implicit 3d representations without 3d supervision,

    M. Niemeyer, L. Mescheder, M. Oechsle, and A. Geiger, “Differ- entiable volumetric rendering: Learning implicit 3d representations without 3d supervision,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2020, pp. 3504–3515. 22

    work page 2020

  9. [9]

    Local deep implicit functions for 3d shape,

    K. Genova, F. Cole, A. Sud, A. Sarna, and T. Funkhouser, “Local deep implicit functions for 3d shape,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2020, pp. 4857–4866

    work page 2020

  10. [10]

    Deepsdf: Learning continuous signed distance functions for shape rep- resentation,

    J. J. Park, P. Florence, J. Straub, R. Newcombe, and S. Lovegrove, “Deepsdf: Learning continuous signed distance functions for shape rep- resentation,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , 2019, pp. 165–174

    work page 2019

  11. [11]

    Neural volume rendering: Nerf and beyond,

    F. Dellaert and L. Yen-Chen, “Neural volume rendering: Nerf and beyond,” arXiv preprint arXiv:2101.05204 , 2020

    work page arXiv 2020

  12. [12]

    Neural fields in visual computing and beyond,

    Y . Xie, T. Takikawa, S. Saito, O. Litany, S. Yan, N. Khan, F. Tombari, J. Tompkin, V . Sitzmann, and S. Sridhar, “Neural fields in visual computing and beyond,” in Computer Graphics Forum, vol. 41, no. 2. Wiley Online Library, 2022, pp. 641–676

    work page 2022

  13. [13]

    Multimodal image synthesis and editing: A survey,

    F. Zhan, Y . Yu, R. Wu, J. Zhang, and S. Lu, “Multimodal image synthesis and editing: A survey,” arXiv preprint arXiv:2112.13592 , 2021

    work page arXiv 2021

  14. [14]

    Clip-nerf: Text-and- image driven manipulation of neural radiance fields,

    C. Wang, M. Chai, M. He, D. Chen, and J. Liao, “Clip-nerf: Text-and- image driven manipulation of neural radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, 2022, pp. 3835–3844

    work page 2022

  15. [15]

    Ad- nerf: Audio driven neural radiance fields for talking head synthesis,

    Y . Guo, K. Chen, S. Liang, Y .-J. Liu, H. Bao, and J. Zhang, “Ad- nerf: Audio driven neural radiance fields for talking head synthesis,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 5784–5794

    work page 2021

  16. [16]

    Zero-shot text-guided object generation with dream fields,

    A. Jain, B. Mildenhall, J. T. Barron, P. Abbeel, and B. Poole, “Zero-shot text-guided object generation with dream fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 867–876

    work page 2022

  17. [17]

    Cg-nerf: Conditional generative neural radiance fields,

    K. Jo, G. Shim, S. Jung, S. Yang, and J. Choo, “Cg-nerf: Conditional generative neural radiance fields,” IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) , 2023

    work page 2023

  18. [18]

    Ide-3d: Interactive disentangled editing for high-resolution 3d-aware portrait synthesis,

    J. Sun, X. Wang, Y . Shi, L. Wang, J. Wang, and Y . Liu, “Ide-3d: Interactive disentangled editing for high-resolution 3d-aware portrait synthesis,” arXiv preprint arXiv:2205.15517 , 2022

    work page arXiv 2022

  19. [19]

    Sem2nerf: Converting single-view semantic masks to neural radiance fields,

    Y . Chen, Q. Wu, C. Zheng, T.-J. Cham, and J. Cai, “Sem2nerf: Converting single-view semantic masks to neural radiance fields,” European conference on computer vision , 2022

    work page 2022

  20. [20]

    Advances in neural rendering,

    A. Tewari, J. Thies, B. Mildenhall, P. Srinivasan, E. Tretschk, W. Yifan, C. Lassner, V . Sitzmann, R. Martin-Brualla, S. Lombardi et al. , “Advances in neural rendering,” in Computer Graphics Forum, vol. 41, no. 2. Wiley Online Library, 2022, pp. 703–735

    work page 2022

  21. [21]

    Ray tracing volume densities,

    J. T. Kajiya and B. P. V on Herzen, “Ray tracing volume densities,”ACM SIGGRAPH computer graphics , vol. 18, no. 3, pp. 165–174, 1984

    work page 1984

  22. [22]

    Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs,

    M. Niemeyer, J. T. Barron, B. Mildenhall, M. S. Sajjadi, A. Geiger, and N. Radwan, “Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 5480–5490

    work page 2022

  23. [23]

    Depth-supervised nerf: Fewer views and faster training for free,

    K. Deng, A. Liu, J.-Y . Zhu, and D. Ramanan, “Depth-supervised nerf: Fewer views and faster training for free,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 12 882–12 891

    work page 2022

  24. [24]

    Nerfren: Neural radiance fields with reflections,

    Y .-C. Guo, D. Kang, L. Bao, Y . He, and S.-H. Zhang, “Nerfren: Neural radiance fields with reflections,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 18 409–18 418

    work page 2022

  25. [25]

    Sinnerf: Training neural radiance fields on complex scenes from a single image,

    D. Xu, Y . Jiang, P. Wang, Z. Fan, H. Shi, and Z. Wang, “Sinnerf: Training neural radiance fields on complex scenes from a single image,” 2022

    work page 2022

  26. [26]

    Fourier features let networks learn high frequency functions in low dimensional domains,

    M. Tancik, P. Srinivasan, B. Mildenhall, S. Fridovich-Keil, N. Ragha- van, U. Singhal, R. Ramamoorthi, J. Barron, and R. Ng, “Fourier features let networks learn high frequency functions in low dimensional domains,”Advances in Neural Information Processing Systems, vol. 33, pp. 7537–7547, 2020

    work page 2020

  27. [27]

    Beyond periodicity: towards a unifying framework for activations in coordinate-mlps,

    S. Ramasinghe and S. Lucey, “Beyond periodicity: towards a unifying framework for activations in coordinate-mlps,” in Computer Vision– ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23– 27, 2022, Proceedings, Part XXXIII . Springer, 2022, pp. 142–158

    work page 2022

  28. [28]

    Large scale multi-view stereopsis evaluation,

    R. Jensen, A. Dahl, G. V ogiatzis, E. Tola, and H. Aanæs, “Large scale multi-view stereopsis evaluation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 406– 413

    work page 2014

  29. [29]

    Bouguet, Camera Calibration Toolbox for Matlab

    J.-Y . Bouguet, Camera Calibration Toolbox for Matlab. CaltechDATA, May 2022. [Online]. Available: https://data.caltech.edu/records/20164

    work page 2022

  30. [30]

    Scannet: Richly-annotated 3d reconstructions of indoor scenes,

    A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner, “Scannet: Richly-annotated 3d reconstructions of indoor scenes,” in Proceedings of the IEEE conference on computer vision and pattern recognition , 2017, pp. 5828–5839

    work page 2017

  31. [31]

    Bundlefu- sion: Real-time globally consistent 3d reconstruction using on-the-fly surface re-integration,

    A. Dai, M. Nießner, M. Zoll ¨ofer, S. Izadi, and C. Theobalt, “Bundlefu- sion: Real-time globally consistent 3d reconstruction using on-the-fly surface re-integration,” ACM Transactions on Graphics 2017 (TOG) , 2017

    work page 2017

  32. [32]

    ShapeNet: An Information-Rich 3D Model Repository

    A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su et al. , “Shapenet: An information-rich 3d model repository,” arXiv preprint arXiv:1512.03012, 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  33. [33]

    Tanks and temples: Benchmarking large-scale scene reconstruction,

    A. Knapitsch, J. Park, Q.-Y . Zhou, and V . Koltun, “Tanks and temples: Benchmarking large-scale scene reconstruction,” ACM Transactions on Graphics (ToG), vol. 36, no. 4, pp. 1–13, 2017

    work page 2017

  34. [34]

    Matterport3D: Learning from RGB-D Data in Indoor Environments

    A. Chang, A. Dai, T. Funkhouser, M. Halber, M. Niessner, M. Savva, S. Song, A. Zeng, and Y . Zhang, “Matterport3d: Learning from rgb-d data in indoor environments,” arXiv preprint arXiv:1709.06158 , 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  35. [35]

    The Replica Dataset: A Digital Replica of Indoor Spaces

    J. Straub, T. Whelan, L. Ma, Y . Chen, E. Wijmans, S. Green, J. J. Engel, R. Mur-Artal, C. Ren, S. Verma et al. , “The replica dataset: A digital replica of indoor spaces,” arXiv preprint arXiv:1906.05797 , 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1906

  36. [36]

    JaxNeRF: an efficient JAX implementation of NeRF,

    B. Deng, J. T. Barron, and P. P. Srinivasan, “JaxNeRF: an efficient JAX implementation of NeRF,” 2020. [Online]. Available: https://github.com/google-research/google-research/tree/master/jaxnerf

    work page 2020

  37. [37]

    Neural sparse voxel fields,

    L. Liu, J. Gu, K. Z. Lin, T.-S. Chua, and C. Theobalt, “Neural sparse voxel fields,” NeurIPS, 2020

    work page 2020

  38. [38]

    Baking neural radiance fields for real-time view synthesis,

    P. Hedman, P. P. Srinivasan, B. Mildenhall, J. T. Barron, and P. De- bevec, “Baking neural radiance fields for real-time view synthesis,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 5875–5884

    work page 2021

  39. [39]

    PlenOctrees for real-time rendering of neural radiance fields,

    A. Yu, R. Li, M. Tancik, H. Li, R. Ng, and A. Kanazawa, “PlenOctrees for real-time rendering of neural radiance fields,” in ICCV, 2021

    work page 2021

  40. [40]

    Fastnerf: High-fidelity neural rendering at 200fps,

    S. J. Garbin, M. Kowalski, M. Johnson, J. Shotton, and J. Valentin, “Fastnerf: High-fidelity neural rendering at 200fps,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 14 346–14 355

    work page 2021

  41. [41]

    Kilonerf: Speeding up neural radiance fields with thousands of tiny mlps,

    C. Reiser, S. Peng, Y . Liao, and A. Geiger, “Kilonerf: Speeding up neural radiance fields with thousands of tiny mlps,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 14 335–14 345

    work page 2021

  42. [42]

    Instant neural graph- ics primitives with a multiresolution hash encoding.ACM Transactions on Graphics (Proc

    T. M ¨uller, A. Evans, C. Schied, and A. Keller, “Instant neural graphics primitives with a multiresolution hash encoding,” ACM Trans. Graph., vol. 41, no. 4, pp. 102:1–102:15, Jul. 2022. [Online]. Available: https://doi.org/10.1145/3528223.3530127

    work page doi:10.1145/3528223.3530127 2022

  43. [43]

    Plenoxels: Radiance fields without neural networks

    A. Yu, S. Fridovich-Keil, M. Tancik, Q. Chen, B. Recht, and A. Kanazawa, “Plenoxels: Radiance fields without neural networks,” arXiv preprint arXiv:2112.05131 , 2021

    work page arXiv 2021

  44. [44]

    Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction,

    C. Sun, M. Sun, and H.-T. Chen, “Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction,” in Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5459–5469

    work page 2022

  45. [45]

    Tensorf: Tensorial radiance fields,

    A. Chen, Z. Xu, A. Geiger, J. Yu, and H. Su, “Tensorf: Tensorial radiance fields,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXII. Springer, 2022, pp. 333–350

    work page 2022

  46. [46]

    Mip-nerf: A multiscale representation for anti- aliasing neural radiance fields,

    J. T. Barron, B. Mildenhall, M. Tancik, P. Hedman, R. Martin-Brualla, and P. P. Srinivasan, “Mip-nerf: A multiscale representation for anti- aliasing neural radiance fields,” in Proceedings of the IEEE/CVF International Conference on Computer Vision , 2021, pp. 5855–5864

    work page 2021

  47. [47]

    Ref-nerf: Structured view-dependent appearance for neural radiance fields,

    D. Verbin, P. Hedman, B. Mildenhall, T. Zickler, J. T. Barron, and P. P. Srinivasan, “Ref-nerf: Structured view-dependent appearance for neural radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 5491–5500

    work page 2022

  48. [48]

    Mvsnerf: Fast generalizable radiance field reconstruction from multi- view stereo,

    A. Chen, Z. Xu, F. Zhao, X. Zhang, F. Xiang, J. Yu, and H. Su, “Mvsnerf: Fast generalizable radiance field reconstruction from multi- view stereo,” inProceedings of the IEEE/CVF International Conference on Computer Vision , 2021, pp. 14 124–14 133

    work page 2021

  49. [49]

    Putting nerf on a diet: Semantically consistent few-shot view synthesis,

    A. Jain, M. Tancik, and P. Abbeel, “Putting nerf on a diet: Semantically consistent few-shot view synthesis,” in Proceedings of the IEEE/CVF International Conference on Computer Vision , 2021, pp. 5885–5894

    work page 2021

  50. [50]

    Mine: Towards continuous depth mpi with nerf for novel view synthesis,

    J. Li, Z. Feng, Q. She, H. Ding, C. Wang, and G. H. Lee, “Mine: Towards continuous depth mpi with nerf for novel view synthesis,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 12 578–12 588

    work page 2021

  51. [51]

    Panoptic neural fields: A semantic object-aware neural scene representation,

    A. Kundu, K. Genova, X. Yin, A. Fathi, C. Pantofaru, L. J. Guibas, A. Tagliasacchi, F. Dellaert, and T. Funkhouser, “Panoptic neural fields: A semantic object-aware neural scene representation,” in Proceedings 23 of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, 2022, pp. 12 871–12 881

    work page 2022

  52. [52]

    Are we ready for autonomous driving? the kitti vision benchmark suite,

    A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,” in Conference on Computer Vision and Pattern Recognition (CVPR) , 2012

    work page 2012

  53. [53]

    Vision meets robotics: The kitti dataset,

    A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, “Vision meets robotics: The kitti dataset,” The International Journal of Robotics Research , vol. 32, no. 11, pp. 1231–1237, 2013

    work page 2013

  54. [54]

    A new performance measure and evaluation benchmark for road detection algorithms,

    J. Fritsch, T. Kuehnl, and A. Geiger, “A new performance measure and evaluation benchmark for road detection algorithms,” in International Conference on Intelligent Transportation Systems (ITSC) , 2013

    work page 2013

  55. [55]

    Object scene flow for autonomous vehicles,

    M. Menze and A. Geiger, “Object scene flow for autonomous vehicles,” in Conference on Computer Vision and Pattern Recognition (CVPR) , 2015

    work page 2015

  56. [56]

    Kitti-360: A novel dataset and benchmarks for urban scene understanding in 2d and 3d,

    Y . Liao, J. Xie, and A. Geiger, “Kitti-360: A novel dataset and benchmarks for urban scene understanding in 2d and 3d,” IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022

    work page 2022

  57. [57]

    Scalability in perception for autonomous driving: Waymo open dataset,

    P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V . Patnaik, P. Tsui, J. Guo, Y . Zhou, Y . Chai, B. Caine et al. , “Scalability in perception for autonomous driving: Waymo open dataset,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , 2020, pp. 2446–2454

    work page 2020

  58. [58]

    Nerfies: Deformable neural radiance fields,

    K. Park, U. Sinha, J. T. Barron, S. Bouaziz, D. B. Goldman, S. M. Seitz, and R. Martin-Brualla, “Nerfies: Deformable neural radiance fields,” ICCV, 2021

    work page 2021

  59. [59]

    Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields,

    K. Park, U. Sinha, P. Hedman, J. T. Barron, S. Bouaziz, D. B. Goldman, R. Martin-Brualla, and S. M. Seitz, “Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields,” ACM Trans. Graph., vol. 40, no. 6, dec 2021

    work page 2021

  60. [60]

    Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans,

    S. Peng, Y . Zhang, Y . Xu, Q. Wang, Q. Shuai, H. Bao, and X. Zhou, “Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, 2021, pp. 9054–9063

    work page 2021

  61. [61]

    Neuman: Neural human radiance field from a single video,

    W. Jiang, K. M. Yi, G. Samei, O. Tuzel, and A. Ranjan, “Neuman: Neural human radiance field from a single video,” in Computer Vision– ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23– 27, 2022, Proceedings, Part XXXII . Springer, 2022, pp. 402–418

    work page 2022

  62. [62]

    Panoptic studio: A massively multiview system for social motion capture,

    H. Joo, H. Liu, L. Tan, L. Gui, B. Nabbe, I. Matthews, T. Kanade, S. Nobuhara, and Y . Sheikh, “Panoptic studio: A massively multiview system for social motion capture,” in Proceedings of the IEEE Inter- national Conference on Computer Vision , 2015, pp. 3334–3342

    work page 2015

  63. [63]

    Image quality assessment: from error visibility to structural similarity,

    Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE transactions on image processing , vol. 13, no. 4, pp. 600–612, 2004

    work page 2004

  64. [64]

    The unreasonable effectiveness of deep features as a perceptual metric,

    R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 586–595

    work page 2018

  65. [65]

    SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

    F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and¡ 0.5 mb model size,” arXiv preprint arXiv:1602.07360, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  66. [66]

    Very Deep Convolutional Networks for Large-Scale Image Recognition

    K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556 , 2014

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  67. [67]

    Imagenet classification with deep convolutional neural networks,

    A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural infor- mation processing systems , vol. 25, 2012

    work page 2012

  68. [68]

    Nerf in the dark: High dynamic range view synthesis from noisy raw images,

    B. Mildenhall, P. Hedman, R. Martin-Brualla, P. P. Srinivasan, and J. T. Barron, “Nerf in the dark: High dynamic range view synthesis from noisy raw images,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 16 190–16 199

    work page 2022

  69. [69]

    Dense depth priors for neural radiance fields from sparse input views,

    B. Roessle, J. T. Barron, B. Mildenhall, P. P. Srinivasan, and M. Nießner, “Dense depth priors for neural radiance fields from sparse input views,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 12 892–12 901

    work page 2022

  70. [70]

    Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo,

    Y . Wei, S. Liu, Y . Rao, W. Zhao, J. Lu, and J. Zhou, “Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 5610–5619

    work page 2021

  71. [71]

    Urban radiance fields,

    K. Rematas, A. Liu, P. P. Srinivasan, J. T. Barron, A. Tagliasacchi, T. Funkhouser, and V . Ferrari, “Urban radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition, 2022, pp. 12 932–12 942

    work page 2022

  72. [72]

    Point-nerf: Point-based neural radiance fields,

    Q. Xu, Z. Xu, J. Philip, S. Bi, Z. Shu, K. Sunkavalli, and U. Neumann, “Point-nerf: Point-based neural radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2022, pp. 5438–5448

    work page 2022

  73. [73]

    Autoint: Automatic integration for fast neural volume rendering,

    D. B. Lindell, J. N. Martel, and G. Wetzstein, “Autoint: Automatic integration for fast neural volume rendering,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2021, pp. 14 556–14 565

    work page 2021

  74. [74]

    pixelNeRF: Neural radiance fields from one or few images,

    A. Yu, V . Ye, M. Tancik, and A. Kanazawa, “pixelNeRF: Neural radiance fields from one or few images,” in CVPR, 2021

    work page 2021

  75. [75]

    Neural rays for occlusion-aware image-based rendering,

    Y . Liu, S. Peng, L. Liu, Q. Wang, P. Wang, C. Theobalt, X. Zhou, and W. Wang, “Neural rays for occlusion-aware image-based rendering,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7824–7833

    work page 2022

  76. [76]

    Giraffe: Representing scenes as composi- tional generative neural feature fields,

    M. Niemeyer and A. Geiger, “Giraffe: Representing scenes as composi- tional generative neural feature fields,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2021, pp. 11 453–11 464

    work page 2021

  77. [77]

    Graf: Generative radiance fields for 3d-aware image synthesis,

    K. Schwarz, Y . Liao, M. Niemeyer, and A. Geiger, “Graf: Generative radiance fields for 3d-aware image synthesis,” Advances in Neural Information Processing Systems , vol. 33, pp. 20 154–20 166, 2020

    work page 2020

  78. [78]

    pi- gan: Periodic implicit generative adversarial networks for 3d-aware image synthesis,

    E. R. Chan, M. Monteiro, P. Kellnhofer, J. Wu, and G. Wetzstein, “pi- gan: Periodic implicit generative adversarial networks for 3d-aware image synthesis,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , 2021, pp. 5799–5809

    work page 2021

  79. [79]

    Gnerf: Gan-based neural radiance field without posed camera,

    Q. Meng, A. Chen, H. Luo, M. Wu, H. Su, L. Xu, X. He, and J. Yu, “Gnerf: Gan-based neural radiance field without posed camera,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 6351–6361

    work page 2021

  80. [80]

    Stylenerf: A style-based 3d aware generator for high-resolution image synthesis,

    J. Gu, L. Liu, P. Wang, and C. Theobalt, “Stylenerf: A style-based 3d aware generator for high-resolution image synthesis,” in Tenth International Conference on Learning Representations , 2022, pp. 1– 25

    work page 2022

Showing first 80 references.