mlsanityData to 7 Oct 2026

NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

arXiv 2106.10689 ↗First posted 20 Jun 2021cs.CV cs.GRcited by 1,701

Not on the map. Why?

Cited by 130 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision, easily get trapped in local minima, and therefore struggle with the reconstruction of objects with severe self-occlusion or thin structures. Meanwhile, recent neural methods for novel view synthesis, such as NeRF and its variants, use volume rendering to produce a neural scene representation with robustness of optimization, even for highly complex objects. However, extracting high-quality surfaces from this learned implicit representation is difficult because there are not sufficient surface constraints in the representation. In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation. We observe that the conventional volume rendering method causes inherent geometric errors (i.e. bias) for surface reconstruction, and therefore propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision. Experiments on the DTU dataset and the BlendedMVS dataset show that NeuS outperforms the state-of-the-arts in high-quality surface reconstruction, especially for objects and scenes with complex structures and self-occlusion.

Key facts. Cited by 1,701 papers in the map (data through 7 Oct 2026). Builds on 33 of its 54 references that are in the map. First posted on arXiv 20 Jun 2021.

Builds on

33 of 54 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  7. 2020Neural Sparse Voxel Fieldscited by 959
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2020Convolutional Occupancy Networkscited by 760
  12. 2020Implicit Geometric Regularization for Learning Shapescited by 707
21 more
  1. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  2. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  3. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  5. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  6. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  7. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  8. 2017Neural 3D Mesh Renderercited by 437
  9. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  10. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  11. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  12. 2017Learning a Multi-View Stereo Machinecited by 194
  13. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  14. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  15. 2019SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimizationcited by 159
  16. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  17. 2021Neural Lumigraph Renderingcited by 105
  18. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  19. 20183D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Imagecited by 40
  20. 2020Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representationscited by 39
  21. 2020Vid2Curve: Simultaneous Camera Motion Estimation and Thin Structure Reconstruction from an RGB Videocited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 27; 2022: 175; 2023: 419; 2024: 574; 2025: 327; 2026: 179.

1,701 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  5. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  6. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  7. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  8. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  9. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  10. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  11. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  12. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
38 more
  1. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  2. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  3. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  4. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  7. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  8. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  9. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  10. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  11. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  12. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  13. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  14. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  15. 2021Advances in Neural Renderingcited by 365
  16. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  17. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  18. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  19. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  20. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  21. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  22. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  23. 20243D Reconstruction with Spatial Memorycited by 269
  24. 2021Urban Radiance Fieldscited by 263
  25. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  26. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  27. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  28. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  29. 2022Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Renderingcited by 217
  30. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  31. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  32. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  33. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  34. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  35. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  36. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  37. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  38. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188

50 most cited of 1,701 All 1,701 (JSON)