Research map / 3D vision / NeRF and radiance fields
PANDORA: Polarization-Aided Neural Decomposition of Radiance
Akshat Dave, Yongyi Zhao, Ashok Veeraraghavan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add polarization (Stokes loss) on top of IllumNet (ablation) | PANDORA · Bust (rendered) | normals MAE (deg): 4.83 -> 1.95 | Improved |
| add polarization (Stokes loss) on top of IllumNet (ablation) | PANDORA · Sphere (rendered) | normals MAE (deg): 1.92 -> 1.04 | Improved |
| add polarization (Stokes loss) on top of IllumNet (ablation) | PANDORA · Bust (rendered) | diffuse PSNR: 25.78 -> 29.53 | Improved |
| add polarization (Stokes loss) on top of IllumNet (ablation) | PANDORA · Sphere (rendered) | diffuse PSNR: 22.20 -> 24.29 | Improved |
| add IllumNet to the intensity-only model (ablation) | PANDORA without polarization · Bust (rendered) | diffuse PSNR: 28.29 -> 25.78 | Hurt |
| add IllumNet to the intensity-only model (ablation) | PANDORA without polarization · Bust (rendered) | normals MAE (deg): 7.89 -> 4.83 | Improved |
| add IllumNet to the intensity-only model (ablation) | PANDORA without polarization · Sphere (rendered) | specular PSNR: 16.23 -> 21.30 | Improved |
| add polarization on top of IllumNet (ablation) | PANDORA · Sphere (rendered) | specular PSNR: 21.30 -> 21.29 | No clear effect |
| use PANDORA instead of PhySG | radiance decomposition · Bust (rendered) | normals MAE (deg): 9.81 -> 3.91 | Improved |
| use PANDORA instead of PhySG | radiance decomposition · Sphere (rendered) | mesh Hausdorff distance: 0.011 -> 0.003 | Improved |
| use PANDORA instead of PhySG | radiance decomposition · Bust (rendered) | specular PSNR: 23.00 -> 22.96 | Mixed |
| use PANDORA instead of NeuralPIL | radiance decomposition · Bust (rendered) | mixed PSNR: 26.71 -> 22.79 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- NeuralPIL — Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition (NeurIPS 2021) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.88)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.88)
- Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects (CVPR 2025 · similarity 0.87)
- Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields (CVPR 2024 · similarity 0.87)
- Differentiable Neural Surface Refinement for Modeling Transparent Objects (CVPR 2024 · similarity 0.87)
- RobIR: Robust Inverse Rendering for High-Illumination Scenes (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
