# GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors

arXiv: https://arxiv.org/abs/2403.11899 · HTML: https://mlsanity.com/paper/2403.11899/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 18 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [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)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [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)
- [Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks](https://mlsanity.com/paper/1901.06523/) (2019)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction](https://mlsanity.com/paper/2205.15848/) (2022)
- [NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images](https://mlsanity.com/paper/2305.17398/) (2023)
- [Improving neural implicit surfaces geometry with patch warping](https://mlsanity.com/paper/2112.09648/) (2021)
- [Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection](https://mlsanity.com/paper/2303.10840/) (2023)
- [PANDORA: Polarization-Aided Neural Decomposition Of Radiance](https://mlsanity.com/paper/2203.13458/) (2022)
- [Polarimetric Multi-View Inverse Rendering](https://mlsanity.com/paper/2007.08830/) (2020)
- [Perspective Phase Angle Model for Polarimetric 3D Reconstruction](https://mlsanity.com/paper/2207.09629/) (2022)

## Built on by (most cited first, 5 of 5)

- [PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction](https://mlsanity.com/paper/2509.19726/) (2025)
- [Glossy Object Reconstruction with Cost-effective Polarized Acquisition](https://mlsanity.com/paper/2504.07025/) (2025)
- [PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery](https://mlsanity.com/paper/2512.00794/) (2025)
- [PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenes](https://mlsanity.com/paper/2512.02664/) (2025)
- [PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction](https://mlsanity.com/paper/2603.10801/) (2026)

## Abstract (arXiv)

Learning surfaces from neural radiance field (NeRF) became a rising topic in Multi-View Stereo (MVS). Recent Signed Distance Function (SDF)-based methods demonstrated their ability to reconstruct accurate 3D shapes of Lambertian scenes. However, their results on reflective scenes are unsatisfactory due to the entanglement of specular radiance and complicated geometry. To address the challenges, we propose a Gaussian-based representation of normals in SDF fields. Supervised by polarization priors, this representation guides the learning of geometry behind the specular reflection and captures more details than existing methods. Moreover, we propose a reweighting strategy in the optimization process to alleviate the noise issue of polarization priors. To validate the effectiveness of our design, we capture polarimetric information, and ground truth meshes in additional reflective scenes with various geometry. We also evaluated our framework on the PANDORA dataset. Comparisons prove our method outperforms existing neural 3D reconstruction methods in reflective scenes by a large margin.