mlsanityData to 14 Oct 2026

Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail

arXiv 2309.10336 ↗First posted 19 Sep 2023cs.CV cs.GRcited by 23

Not on the map. Why?

Abstract (arXiv)

We present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance. Our representation aggregates space features from a multi-convolved featurization within a conical frustum along a ray and optimizes the LoD feature volume through differentiable rendering. Additionally, we propose an error-guided sampling strategy to guide the growth of the SDF during the optimization. Both qualitative and quantitative evaluations demonstrate that our method achieves superior surface reconstruction and photorealistic view synthesis compared to state-of-the-art approaches.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 32 of its 60 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

32 of 60 references.

References · 32

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  7. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  8. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  9. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  10. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  11. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  12. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
20 more
  1. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  2. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  3. 2021Advances in Neural Renderingcited by 365
  4. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  5. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  6. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  7. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  8. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  9. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  10. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  11. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 114
  12. 2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
  13. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  14. 2019End-to-End Wireframe Parsingcited by 72
  15. 2023PET-NeuS: Positional Encoding Tri-Planes for Neural Surfacescited by 37
  16. 2023High-Fidelity 3D Face Generation from Natural Language Descriptionscited by 33
  17. 2023Local Implicit Ray Function for Generalizable Radiance Field Representationcited by 19
  18. 2023NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illuminationcited by 10
  19. 2023Inverting the Imaging Process by Learning an Implicit Camera Modelcited by 10
  20. 2023HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfacescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 12; 2025: 3; 2026: 5.

23 papers.

Sort:

  1. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  2. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 192
  3. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  4. 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 67
  5. 2024Advances in 3D Generation: A Surveycited by 63
  6. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  7. 2024Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesiscited by 41
  8. 2024NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstructioncited by 16
  9. 2023City-on-Web: Real-time Neural Rendering of Large-scale Scenes on the Webcited by 14
  10. 2024BANF: Band-limited Neural Fields for Levels of Detail Reconstructioncited by 10
  11. 2025Anti-Aliased 2D Gaussian Splattingcited by 7
  12. 2024Neural Gaussian Scale-Space Fieldscited by 6
11 more
  1. 2024G3DR: Generative 3D Reconstruction in ImageNetcited by 5
  2. 2025LOD-GS: Level-of-Detail-Sensitive 3D Gaussian Splatting for Detail Conserved Anti-Aliasingcited by 3
  3. 2023RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fieldscited by 2
  4. 2024MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representationscited by 0
  5. 2024VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolationcited by 0
  6. 20253D Surface Reconstruction with Enhanced High-Frequency Detailscited by 0
  7. 2026HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representationscited by 0
  8. 2026ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatarscited by 0
  9. 2026High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representationcited by 0
  10. 2026Recent Advances and Trends in Learning-based 3D Representationscited by 0
  11. 2026Towards Alias-Free 4D Gaussian Representations with Motion-Aware Filteringcited by 0