mlsanityData to 19 Oct 2026

Neural surface reconstruction

446 papers0 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: surface, reconstruction, neural, surface reconstruction, point

Key facts. Neural surface reconstruction: 446 papers on arXiv since 2021 (data through 19 Oct 2026). 189 of its 446 mapped papers (42%) cite “NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction” (2021, arXiv 2106.10689). 8 new papers 1 Oct–19 Oct.

What’s new

1 Oct – 19 Oct 2026

8 new papers, 1 Oct – 19 Oct; 0 this week.

  1. Earlier · 8
  2. MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
  3. Surface Reconstruction from Range Scans Under Visibility Constraints
  4. Uncertainty-Aware Cortical Surface Reconstruction and Spherical Registration for Heterogeneous Brain MRI
  5. Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction also fits: Sparse-input reconstruction
  6. Complexity-Calibrated Reconstruction Discrepancy for No-Reference Point Cloud Quality Assessment
  7. Volume Rendering with Metric--Phase Fields for Thin Structures and Sign-Ambiguous Geometry
  8. SimCortex v2: Joint Cortical Surface Reconstruction with Near-Zero Collisions and Self-Intersections
  9. A Three-Dimensional Reverse-Projection Method for Sparse Point Cloud Completion and Its Application to High-Speed Train Nose Reconstruction also fits: SLAM and driving scene reconstruction

Foundations

Most cited by papers here

  1. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction2021cited by 189 here
  2. UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction2021cited by 128 here
  3. MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction2022cited by 86 here
  4. Neuralangelo: High-Fidelity Neural Surface Reconstruction2023cited by 71 here
  5. Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction2022cited by 60 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 128 here
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 189 here
  3. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 38 here
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 86 here
  5. 2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 32 here
  6. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 55 here
  7. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 71 here
  8. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 34 here
16 more it builds on, not in this chain
  1. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 48 here
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 34 here
  3. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 31 here
  4. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 42 here
  5. 2021Neural RGB-D Surface Reconstructioncited by 37 here
  6. 2021Shape As Points: A Differentiable Poisson Solvercited by 48 here
  7. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 32 here
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 40 here
  9. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 36 here
  10. 2021Improving neural implicit surfaces geometry with patch warpingcited by 56 here
  11. 2022POCO: Point Convolution for Surface Reconstructioncited by 33 here
  12. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 60 here
  13. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 38 here
  14. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 40 here
  15. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 51 here
  16. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 79 here

The 24 most cited of 832.

Browse

30 of 446, ranked 6–35

  1. 6Improving neural implicit surfaces geometry with patch warping202156
  2. 7NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction202255
  3. 8NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors202251
  4. 9Shape As Points: A Differentiable Poisson Solver202148
  5. 10NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video202142
  6. 11HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details202240
  7. 12SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Views202238
  8. 13POCO: Point Convolution for Surface Reconstruction202233
  9. 14Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction202232
  10. 15Learning Signed Distance Field for Multi-view Surface Reconstruction202132
All 30
  1. 16Deep Implicit Moving Least-Squares Functions for 3D Reconstruction202125
  2. 17DiGS : Divergence guided shape implicit neural representation for unoriented point clouds202124
  3. 18Critical Regularizations for Neural Surface Reconstruction in the Wild202221
  4. 19NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies202219
  5. 20VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction202219
  6. 21SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks202119
  7. 22BANMo: Building Animatable 3D Neural Models from Many Casual Videos202119
  8. 23GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction202217
  9. 24LASR: Learning Articulated Shape Reconstruction from a Monocular Video202116
  10. 25Surface Reconstruction from Point Clouds: A Survey and a Benchmark202214
  11. 26Object-Compositional Neural Implicit Surfaces202214
  12. 27CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization202214
  13. 28PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices202214
  14. 29Neural Kernel Surface Reconstruction202313
  15. 30Surface Reconstruction from Point Clouds by Learning Predictive Context Priors202213
  16. 31PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo202213
  17. 32Neural Fields as Learnable Kernels for 3D Reconstruction202113
  18. 33HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization202312
  19. 34Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection202311
  20. 35VisCo Grids: Surface Reconstruction with Viscosity and Coarea Grids202311