NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics
Chenhao Li, Taishi Ono, Takeshi Uemori, Sho Nitta, Hajime Mihara, Alexander Gatto, Hajime Nagahara, Yusuke Moriuchi
摘要
Roughness Normal Ours Polarization camera Scene with conductors and dielectrics ior (real) ior (imag.) Normal Roughness Diffuse albedo Diffuse albedo Relit image Relit image Figure 1. Comparison of the polarized inverse rendering methods. Since NeISF [33] does not model conductors correctly, its geometry and material reconstruction is poor. Our method estimates the complex refractive index of conductors and re-renders the image via a physicallybased pBRDF. Therefore, the reconstructed material and geometry are accurate, and the relighting result is glossy. We normalize the real and imaginary parts of the complex refractive index ior, and visualize them separately.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface ReconstructionYufei Han, Bowen Tie, Heng Guo, Youwei Lyu 等ICCV 2025 · 被引用 2 次
- PolarGuide-GSDR: 3D Gaussian Splatting Driven by Polarization Priors and Deferred Reflection for Real-World Reflective ScenesDerui Shan, Qian Qiao, Hao Lu, Tao Du 等CVPR 2026 · 被引用 1 次
- Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo CuesXu Cao, Takafumi TaketomiICCV 2025 · 被引用 1 次
它引用的顶会 Paper36
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt 等NeurIPS 2021 · 被引用 2,500 次
- Volume Rendering of Neural Implicit SurfacesLior Yariv, Jiatao Gu, Yoni Kasten, Yaron LipmanNeurIPS 2021 · 被引用 1,421 次
- Multiview Neural Surface Reconstruction by Disentangling Geometry and AppearanceLior Yariv, Yoni Kasten, Dror Moran, Meirav Galun 等NeurIPS 2020 · 被引用 1,010 次
- Implicit Geometric Regularization for Learning ShapesAmos Gropp, Lior Yariv, Niv Haim, Matan Atzmon 等ICML 2020 · 被引用 1,001 次
相关 Paper
- NeISF: Neural Incident Stokes Field for Geometry and Material EstimationChenhao Li, Taishi Ono, Takeshi Uemori, Hajime Mihara 等CVPR 2024
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination VariationHadi Alzayer, Philipp Henzler, Jonathan T. Barron, Jia-Bin Huang 等CVPR 2025
- PBR-NeRF: Inverse Rendering with Physics-Based Neural FieldsSean Wu, Shamik Basu, Tim Broedermann, Luc Van Gool 等CVPR 2025
- Differentiable Inverse Rendering with Interpretable Basis BRDFsHoon-Gyu Chung, Seokjun Choi, Seung-Hwan BaekCVPR 2025
- Ref-GS: Directional Factorization for 2D Gaussian SplattingYoujia Zhang, Anpei Chen, Yumin Wan, Zikai Song 等CVPR 2025
