# SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration

arXiv: https://arxiv.org/abs/2312.04803 · HTML: https://mlsanity.com/paper/2312.04803/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 8 Dec 2023.

## Builds on (most cited first, 25 of 25)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors](https://mlsanity.com/paper/2206.13597/) (2022)
- [NerfAcc: Efficient Sampling Accelerates NeRFs](https://mlsanity.com/paper/2305.04966/) (2023)
- [PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices](https://mlsanity.com/paper/2211.12562/) (2022)
- [PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo](https://mlsanity.com/paper/2207.11406/) (2022)
- [Human Performance Modeling and Rendering via Neural Animated Mesh](https://mlsanity.com/paper/2209.08468/) (2022)
- [Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials](https://mlsanity.com/paper/2001.06659/) (2020)
- [Self-calibrating Deep Photometric Stereo Networks](https://mlsanity.com/paper/1903.07366/) (2019)
- [ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects](https://mlsanity.com/paper/2304.10448/) (2023)
- [Uncertainty-Aware Deep Multi-View Photometric Stereo](https://mlsanity.com/paper/2202.13071/) (2022)
- [Scalable, Detailed and Mask-Free Universal Photometric Stereo](https://mlsanity.com/paper/2303.15724/) (2023)
- [MVPSNet: Fast Generalizable Multi-view Photometric Stereo](https://mlsanity.com/paper/2305.11167/) (2023)
- [Multi-View Azimuth Stereo via Tangent Space Consistency](https://mlsanity.com/paper/2303.16447/) (2023)

## Built on by (most cited first, 18 of 18)

- [Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging](https://mlsanity.com/paper/2503.22236/) (2025)
- [Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set](https://mlsanity.com/paper/2410.14189/) (2024)
- [Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstruction](https://mlsanity.com/paper/2406.04861/) (2024)
- [SplatSDF: Boosting SDF-NeRF via Architecture-Level Fusion with Gaussian Splats](https://mlsanity.com/paper/2411.15468/) (2024)
- [Multi-view Surface Reconstruction Using Normal and Reflectance Cues](https://mlsanity.com/paper/2506.04115/) (2025)
- [NPLMV-PS: Neural Point-Light Multi-View Photometric Stereo](https://mlsanity.com/paper/2405.12057/) (2024)
- [FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images](https://mlsanity.com/paper/2503.19207/) (2025)
- [AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians](https://mlsanity.com/paper/2510.25129/) (2025)
- [FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction](https://mlsanity.com/paper/2410.08282/) (2024)
- [LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo](https://mlsanity.com/paper/2412.16737/) (2024)
- [PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction](https://mlsanity.com/paper/2504.08410/) (2025)
- [Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues](https://mlsanity.com/paper/2507.23162/) (2025)
- [Learning Neural Parametric 3D Breast Shape Models for Metrical Surface Reconstruction From Monocular RGB Videos](https://mlsanity.com/paper/2510.13540/) (2025)
- [Perspective-aware fusion of incomplete depth maps and surface normals for accurate 3D reconstruction](https://mlsanity.com/paper/2602.07444/) (2026)
- [EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups](https://mlsanity.com/paper/2602.24065/) (2026)
- [High-fidelity Multi-view Normal Integration with Scale-encoded Neural Surface Representation](https://mlsanity.com/paper/2603.20337/) (2026)
- [FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash Images](https://mlsanity.com/paper/2608.25360/) (2026)
- [Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows](https://mlsanity.com/paper/2609.15833/) (2026)

## 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.