# Uncertainty-Aware Deep Multi-View Photometric Stereo

arXiv: https://arxiv.org/abs/2202.13071 · HTML: https://mlsanity.com/paper/2202.13071/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 72 references that are in the map.
- First posted on arXiv 26 Feb 2022.

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization](https://mlsanity.com/paper/1912.07109/) (2019)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [Multi-Scale Geometric Consistency Guided Multi-View Stereo](https://mlsanity.com/paper/1904.08103/) (2019)
- [Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume](https://mlsanity.com/paper/1912.11746/) (2019)
- [Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials](https://mlsanity.com/paper/2001.06659/) (2020)
- [Deep Level Sets: Implicit Surface Representations for 3D Shape Inference](https://mlsanity.com/paper/1901.06802/) (2019)
- [Self-calibrating Deep Photometric Stereo Networks](https://mlsanity.com/paper/1903.07366/) (2019)
- [CNN-PS: CNN-based Photometric Stereo for General Non-Convex Surfaces](https://mlsanity.com/paper/1808.10093/) (2018)
- [Neural Inverse Rendering for General Reflectance Photometric Stereo](https://mlsanity.com/paper/1802.10328/) (2018)
- [PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network](https://mlsanity.com/paper/2007.07714/) (2020)
- [Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces](https://mlsanity.com/paper/2012.06777/) (2020)
- [Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames](https://mlsanity.com/paper/1708.04398/) (2017)
- [Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo](https://mlsanity.com/paper/2110.05594/) (2021)
- [A Differential Volumetric Approach to Multi-View Photometric Stereo](https://mlsanity.com/paper/1811.01984/) (2018)
- [Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene](https://mlsanity.com/paper/1911.09092/) (2019)
- [Deep Learning: A Bayesian Perspective](https://mlsanity.com/paper/1706.00473/) (2017)
- [Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo](https://mlsanity.com/paper/2110.05621/) (2021)

## Built on by (most cited first, 30 of 30)

- [PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo](https://mlsanity.com/paper/2207.11406/) (2022)
- [VA-DepthNet: A Variational Approach to Single Image Depth Prediction](https://mlsanity.com/paper/2302.06556/) (2023)
- [SAGS: Structure-Aware 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19149/) (2024)
- [MVPSNet: Fast Generalizable Multi-view Photometric Stereo](https://mlsanity.com/paper/2305.11167/) (2023)
- [SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration](https://mlsanity.com/paper/2312.04803/) (2023)
- [Multi-View Photometric Stereo Revisited](https://mlsanity.com/paper/2210.07670/) (2022)
- [Multi-View Azimuth Stereo via Tangent Space Consistency](https://mlsanity.com/paper/2303.16447/) (2023)
- [MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction](https://mlsanity.com/paper/2503.18363/) (2025)
- [Single Image Depth Prediction Made Better: A Multivariate Gaussian Take](https://mlsanity.com/paper/2303.18164/) (2023)
- [RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction](https://mlsanity.com/paper/2312.01215/) (2023)
- [Relightable Neural Human Assets from Multi-view Gradient Illuminations](https://mlsanity.com/paper/2212.07648/) (2022)
- [nLMVS-Net: Deep Non-Lambertian Multi-View Stereo](https://mlsanity.com/paper/2207.11876/) (2022)
- [Deep Learning Methods for Calibrated Photometric Stereo and Beyond](https://mlsanity.com/paper/2212.08414/) (2022)
- [Normal-guided Detail-Preserving Neural Implicit Function for High-Fidelity 3D Surface Reconstruction](https://mlsanity.com/paper/2406.04861/) (2024)
- [Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo](https://mlsanity.com/paper/2404.00098/) (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)
- [PRM: Photometric Stereo based Large Reconstruction Model](https://mlsanity.com/paper/2412.07371/) (2024)
- [A Neural Height-Map Approach for the Binocular Photometric Stereo Problem](https://mlsanity.com/paper/2311.05958/) (2023)
- [LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereo](https://mlsanity.com/paper/2412.16737/) (2024)
- [A Dual-Perspective Approach to Evaluating Feature Attribution Methods](https://mlsanity.com/paper/2308.08949/) (2023)
- [Mobile Robotic Multi-View Photometric Stereo](https://mlsanity.com/paper/2502.10842/) (2025)
- [Endoscopic Depth Estimation Based on Deep Learning: A Survey](https://mlsanity.com/paper/2507.20881/) (2025)
- [Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere](https://mlsanity.com/paper/2405.16460/) (2024)
- [Evidential Transformers for Improved Image Retrieval](https://mlsanity.com/paper/2409.01082/) (2024)
- [Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues](https://mlsanity.com/paper/2507.23162/) (2025)
- [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)
- [3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark](https://mlsanity.com/paper/2605.12437/) (2026)
- [Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage Workflows](https://mlsanity.com/paper/2609.15833/) (2026)

## Abstract (arXiv)

This paper presents a simple and effective solution to the longstanding classical multi-view photometric stereo (MVPS) problem. It is well-known that photometric stereo (PS) is excellent at recovering high-frequency surface details, whereas multi-view stereo (MVS) can help remove the low-frequency distortion due to PS and retain the global geometry of the shape. This paper proposes an approach that can effectively utilize such complementary strengths of PS and MVS. Our key idea is to combine them suitably while considering the per-pixel uncertainty of their estimates. To this end, we estimate per-pixel surface normals and depth using an uncertainty-aware deep-PS network and deep-MVS network, respectively. Uncertainty modeling helps select reliable surface normal and depth estimates at each pixel which then act as a true representative of the dense surface geometry. At each pixel, our approach either selects or discards deep-PS and deep-MVS network prediction depending on the prediction uncertainty measure. For dense, detailed, and precise inference of the object's surface profile, we propose to learn the implicit neural shape representation via a multilayer perceptron (MLP). Our approach encourages the MLP to converge to a natural zero-level set surface using the confident prediction from deep-PS and deep-MVS networks, providing superior dense surface reconstruction. Extensive experiments on the DiLiGenT-MV benchmark dataset show that our method provides high-quality shape recovery with a much lower memory footprint while outperforming almost all of the existing approaches.