RGB-to-Polarization Estimation: A New Task and Benchmark Study

TL;DR

This paper introduces the novel task of estimating polarization images from RGB images, establishing the first benchmark to evaluate deep learning models and guide future research in this emerging area.

Contribution

It defines the new RGB-to-polarization estimation task and creates a comprehensive benchmark using existing datasets and diverse models for evaluation.

Findings

Benchmark reveals current performance limits

Different model types have distinct strengths and weaknesses

Provides insights for future polarization estimation research

Abstract

Polarization images provide rich physical information that is fundamentally absent from standard RGB images, benefiting a wide range of computer vision applications such as reflection separation and material classification. However, the acquisition of polarization images typically requires additional optical components, which increases both the cost and the complexity of the applications. To bridge this gap, we introduce a new task: RGB-to-polarization image estimation, which aims to infer polarization information directly from RGB images. In this work, we establish the first comprehensive benchmark for this task by leveraging existing polarization datasets and evaluating a diverse set of state-of-the-art deep learning models, including both restoration-oriented and generative architectures. Through extensive quantitative and qualitative analysis, our benchmark not only establishes the current performance ceiling of RGB-to-polarization estimation, but also systematically reveals the respective strengths and limitations of different model families -- such as direct reconstruction versus generative synthesis, and task-specific training versus large-scale pre-training. In addition, we provide some potential directions for future research on polarization estimation. This benchmark is intended to serve as a foundational resource to facilitate the design and evaluation of future methods for polarization estimation from standard RGB inputs.