# PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation

arXiv: https://arxiv.org/abs/2610.08346 · HTML: https://mlsanity.com/paper/2610.08346/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 75 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 7 of 7)

- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024)
- [Explain Before You Answer: A Survey on Compositional Visual Reasoning](https://mlsanity.com/paper/2508.17298/) (2025)
- [Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery](https://mlsanity.com/paper/2502.15224/) (2025)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [OmniRaindrop: A Comprehensive Benchmark for Dual-Focused Raindrop Removal under Day and Night Scenes](https://mlsanity.com/paper/2510.17719/) (2025)
- [GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes](https://mlsanity.com/paper/2605.23602/) (2026)

## Built on by (most cited first, 1 of 1)

- [SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions](https://mlsanity.com/paper/2610.14082/) (2026)

## Abstract (arXiv)

Polarization imaging provides physical cues beyond intensity imaging but typically requires specialized hardware. Recent methods infer polarization from RGB-like inputs, yet predict only normalized Stokes components or relative descriptors, from which the radiometric scale needed for full Stokes reconstruction has been divided out. We introduce PolarScale, a benchmark that makes this scale an explicit prediction and evaluation target. Built on existing trichromatic full-Stokes measurements, PolarScale takes the per-scene normalized total-intensity image s0 (a scene-referred linear image, not a consumer sRGB photograph) and asks models to predict normalized Stokes components, AoLP/DoLP/DoCP, and a per-scene scale. Because the scale is divided out of the input, it is not physically identifiable; PolarScale therefore evaluates dataset-conditioned semantic scale estimation against a constant-scale control, together with angular, self-consistency, and physical-bound metrics. Across seven restoration-based and generative backbones and three prediction strategies, the strongest restoration models estimate the scale with 3.6-4.3% mean relative error versus 5.7% for the constant control and violate physical bounds on fewer than 0.25% of pixels, whereas two generative baselines collapse to a near-zero scale; explicit descriptor supervision improves descriptor accuracy (23.66 vs. 18.88 dB PSNR for MAE). Predicted full-Stokes representations improve diffuse/specular separation, material segmentation, and glare classification, although in diffuse/specular separation the learned scale performs only on par with the constant control.