mlsanityData to 7 Oct 2026

PISR: Polarimetric Neural Implicit Surface Reconstruction for Textureless and Specular Objects

arXiv 2409.14331 ↗First posted 22 Sep 2024cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Neural implicit surface reconstruction has achieved remarkable progress recently. Despite resorting to complex radiance modeling, state-of-the-art methods still struggle with textureless and specular surfaces. Different from RGB images, polarization images can provide direct constraints on the azimuth angles of the surface normals. In this paper, we present PISR, a novel method that utilizes a geometrically accurate polarimetric loss to refine shape independently of appearance. In addition, PISR smooths surface normals in image space to eliminate severe shape distortions and leverages the hash-grid-based neural signed distance function to accelerate the reconstruction. Experimental results demonstrate that PISR achieves higher accuracy and robustness, with an L1 Chamfer distance of 0.5 mm and an F-score of 99.5% at 1 mm, while converging 4~30 times faster than previous polarimetric surface reconstruction methods.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 22 Sep 2024.

Builds on

31 of 56 references.

References · 31

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  3. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  6. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  7. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  8. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  11. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  12. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
19 more
  1. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  2. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 332
  3. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
  4. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
  5. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  6. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  7. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  8. 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 68
  9. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  10. 2022PANDORA: Polarization-Aided Neural Decomposition Of Radiancecited by 52
  11. 2023UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflectionscited by 29
  12. 2020Polarimetric Multi-View Inverse Renderingcited by 28
  13. 2023S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fieldscited by 25
  14. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  15. 2022Transparent Shape from a Single View Polarization Imagecited by 16
  16. 2022Perspective Phase Angle Model for Polarimetric 3D Reconstructioncited by 11
  17. 2021Polarimetric Monocular Dense Mapping Using Relative Deep Depth Priorcited by 8
  18. 2022Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflectioncited by 6
  19. 2023Polarimetric PatchMatch Multi-View Stereocited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 6.

15 papers.

Sort:

By area:

  1. 2024EnvGS: Modeling View-Dependent Appearance with Environment Gaussiancited by 34
  2. 2024NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectricscited by 9
  3. 2025PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstructioncited by 8
  4. 2025PolarAnything: Diffusion-based Polarimetric Image Synthesiscited by 5
  5. 2025Glossy Object Reconstruction with Cost-effective Polarized Acquisitioncited by 3
  6. 2025PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstructioncited by 1
  7. 2025PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recoverycited by 1
  8. 2025PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective Scenescited by 0
  9. 2025TraceFlow: Dynamic 3D Reconstruction of Specular Scenes Driven by Ray Tracingcited by 0
  10. 2026EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setupscited by 0
  11. 2026Revisiting Shape from Polarization in the Era of Vision Foundation Modelscited by 0
  12. 2026PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstructioncited by 0
3 more
  1. 2026Poppy: Polarization-based Plug-and-Play Guidance for Enhancing Monocular Normal Estimationcited by 0
  2. 2026PolarVLM: Bridging the Semantic-Physical Gap in Vision-Language Modelscited by 0
  3. 2026Snapshot Polarimetric Display Inverse Renderingcited by 0