mlsanityData to 14 Oct 2026

PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction

arXiv 2509.19726 ↗First posted 24 Sep 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Efficient shape reconstruction for surfaces with complex reflectance properties is crucial for real-time virtual reality. While 3D Gaussian Splatting (3DGS)-based methods offer fast novel view rendering by leveraging their explicit surface representation, their reconstruction quality lags behind that of implicit neural representations, particularly in the case of recovering surfaces with complex reflective reflectance. To address these problems, we propose PolGS, a Polarimetric Gaussian Splatting model allowing fast reflective surface reconstruction in 10 minutes. By integrating polarimetric constraints into the 3DGS framework, PolGS effectively separates specular and diffuse components, enhancing reconstruction quality for challenging reflective materials. Experimental results on the synthetic and real-world dataset validate the effectiveness of our method.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 24 Sep 2025.

Builds on

33 of 50 references.

References · 33

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  4. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  5. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  6. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  7. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  9. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  10. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  11. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  12. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
21 more
  1. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 232
  2. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  3. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  4. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  5. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 138
  6. 2022HF-NeuS: Improved Surface Reconstruction Using High-Frequency Detailscited by 121
  7. 2024GSDF: 3DGS Meets SDF for Improved Rendering and Reconstructioncited by 83
  8. 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
  9. 2021Deep Polarization Imaging for 3D shape and SVBRDF Acquisitioncited by 56
  10. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  11. 2022PANDORA: Polarization-Aided Neural Decomposition Of Radiancecited by 52
  12. 2020Polarimetric Multi-View Inverse Renderingcited by 28
  13. 2024TensoSDF: Roughness-aware Tensorial Representation for Robust Geometry and Material Reconstructioncited by 26
  14. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  15. 2024NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Imagescited by 22
  16. 2023Multi-View Azimuth Stereo via Tangent Space Consistencycited by 16
  17. 2024Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fieldscited by 16
  18. 2024PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objectscited by 15
  19. 2024NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectricscited by 9
  20. 2024Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimationcited by 6
  21. 2024GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priorscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 7.

8 papers.

  1. 2026Benchmarking PhD-Level Coding in 3D Geometric Computer Visioncited by 2
  2. 2025PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recoverycited by 1
  3. 2026Architectural Unification for Polarimetric Imaging Across Multiple Degradationscited by 1
  4. 2026Revisiting Shape from Polarization in the Era of Vision Foundation Modelscited by 0
  5. 2026PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstructioncited by 0
  6. 2026PhyGaP: Physically-Grounded Gaussians with Polarization Cuescited by 0
  7. 2026Learning Spectral and Polarimetric Clues for One-to-Multimodal Novel View Synthesiscited by 0
  8. 2026Differentiable Polarized Path Tracingcited by 0