Research map / 3D vision / Face and shape
Polarimetric Neural Field via Unified Complex-Valued Wave Representation
Chu Zhou, Yixin Yang, Junda Liao, Heng Guo, Boxin Shi, Imari Sato
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 |
|---|---|---|---|
| represent parameters as a unified complex-valued wave (ablation) | Polarimetric neural field · Firewood scene ablation, DoP | PSNR: 6.63 -> 36.01 | Improved |
| represent parameters as a unified complex-valued wave (ablation) | Polarimetric neural field · Firewood scene ablation, TI | PSNR: 39.22 -> 53.54 | Improved |
| represent parameters as a unified complex-valued wave (ablation) | Polarimetric neural field · Firewood scene ablation, AoP | PSNR: 18.72 -> 17.26 | Hurt |
| add tuning-free demodulation fitting instead of direct fitting (ablation) | Polarimetric neural field · Firewood scene ablation, AoP | PSNR: 11.71 -> 17.26 | Improved |
| add tuning-free demodulation fitting instead of direct fitting (ablation) | Polarimetric neural field · Firewood scene ablation, DoP | PSNR: 39.76 -> 36.01 | Hurt |
| add dedicated AoP branch (ablation) | Polarimetric neural field · Firewood scene ablation, AoP | PSNR: 11.99 -> 17.26 | Improved |
| add dedicated AoP branch (ablation) | Polarimetric neural field · Firewood scene ablation, DoP | PSNR: 37.93 -> 36.01 | Hurt |
| use complex-valued network instead of two real-valued networks (ablation) | Polarimetric neural field · Firewood scene ablation, TI | PSNR: 14.42 -> 53.54 | Improved |
| add alternating merging in c2rMLP (ablation) | Polarimetric neural field · Firewood scene ablation, DoP | PSNR: 35.98 -> 36.01 | Improved |
| add alternating merging in c2rMLP (ablation) | Polarimetric neural field · Firewood scene ablation, AoP | PSNR: 17.04 -> 17.26 | Improved |
| use proposed method instead of pCON | Polarimetric neural field · Firewood scene, TI | PSNR: 39.95 -> 53.54 | Improved |
| use proposed method instead of pCON | Polarimetric neural field · Firewood scene, AoP | PSNR: 17.24 -> 17.26 | No clear effect |
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.
- FINER — FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024) · better on 3 of 4 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
- Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing (NeurIPS 2024 · similarity 0.85)
- High-Fidelity Polarimetric Implicit 3D Reconstruction with View-Dependent Physical Representation (AAAI 2025 · similarity 0.85)
- PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation (NeurIPS 2026 · similarity 0.84)
- Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset (CVPR 2024 · similarity 0.83)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.82)
- GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors (ICLR 2024 · similarity 0.82)
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.
