mlsanityData to 7 Oct 2026

SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration

arXiv 2312.04803 ↗First posted 8 Dec 2023cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

We present SuperNormal, a fast, high-fidelity approach to multi-view 3D reconstruction using surface normal maps. With a few minutes, SuperNormal produces detailed surfaces on par with 3D scanners. We harness volume rendering to optimize a neural signed distance function (SDF) powered by multi-resolution hash encoding. To accelerate training, we propose directional finite difference and patch-based ray marching to approximate the SDF gradients numerically. While not compromising reconstruction quality, this strategy is nearly twice as efficient as analytical gradients and about three times faster than axis-aligned finite difference. Experiments on the benchmark dataset demonstrate the superiority of SuperNormal in efficiency and accuracy compared to existing multi-view photometric stereo methods. On our captured objects, SuperNormal produces more fine-grained geometry than recent neural 3D reconstruction methods.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 8 Dec 2023.

Builds on

25 of 40 references.

References · 25

  1. 2023Segment Anythingcited by 8,158
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  9. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  10. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  11. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  12. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
13 more
  1. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  2. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  3. 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
  4. 2022PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Latticescited by 72
  5. 2022PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereocited by 69
  6. 2022Human Performance Modeling and Rendering via Neural Animated Meshcited by 64
  7. 2020Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materialscited by 56
  8. 2019Self-calibrating Deep Photometric Stereo Networkscited by 47
  9. 2023ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objectscited by 42
  10. 2022Uncertainty-Aware Deep Multi-View Photometric Stereocited by 30
  11. 2023Scalable, Detailed and Mask-Free Universal Photometric Stereocited by 30
  12. 2023MVPSNet: Fast Generalizable Multi-view Photometric Stereocited by 18
  13. 2023Multi-View Azimuth Stereo via Tangent Space Consistencycited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 7; 2026: 5.

18 papers.

Sort:

  1. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 95
  2. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 47
  3. 2024Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstructioncited by 8
  4. 2024SplatSDF: Boosting SDF-NeRF via Architecture-Level Fusion with Gaussian Splatscited by 5
  5. 2025Multi-view Surface Reconstruction Using Normal and Reflectance Cuescited by 5
  6. 2024NPLMV-PS: Neural Point-Light Multi-View Photometric Stereocited by 4
  7. 2025FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Imagescited by 4
  8. 2025AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussianscited by 4
  9. 2024FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstructioncited by 2
  10. 2024LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereocited by 2
  11. 2025PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstructioncited by 1
  12. 2025Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cuescited by 0
6 more
  1. 2025Learning Neural Parametric 3D Breast Shape Models for Metrical Surface Reconstruction From Monocular RGB Videoscited by 0
  2. 2026Perspective-aware fusion of incomplete depth maps and surface normals for accurate 3D reconstructioncited by 0
  3. 2026EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setupscited by 0
  4. 2026High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representationcited by 0
  5. 2026FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash Imagescited by 0
  6. 2026Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflowscited by 0