Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysis

2025-03-24

AI Summary

This work addresses three key challenges in snapshot polarimetric imaging: high sensor noise, low spatial resolution, and the absence of dedicated datasets and reliable noise statistical models. To this end, we introduce PolarNS & PolarBurstSR—the first benchmark dataset for polarimetric image noise statistics and multi-frame super-resolution. We propose a polarization-specific noise modeling framework that quantifies, for the first time, noise propagation across Stokes parameters. A dual-Bayer sensor acquisition system coupled with a controlled dark-room calibration protocol enables accurate real-world noise characterization. Experiments demonstrate that our polarization-tailored super-resolution model outperforms RGB-transfer baselines by over 2.1 dB in PSNR. This work establishes the first standardized data and evaluation benchmark for polarimetric image reconstruction, bridging a critical gap in both noise-robust algorithm development and practical deployment.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Snapshot polarization imaging calculates polarization states from linearly polarized subimages. To achieve this, a polarization camera employs a double Bayer-patterned sensor to capture both color and polarization. It demonstrates low light efficiency and low spatial resolution, resulting in increased noise and compromised polarization measurements. Although burst super-resolution effectively reduces noise and enhances spatial resolution, applying it to polarization imaging poses challenges due to the lack of tailored datasets and reliable ground truth noise statistics. To address these issues, we introduce PolarNS and PolarBurstSR, two innovative datasets developed specifically for polarization imaging. PolarNS provides characterization of polarization noise statistics, facilitating thorough analysis, while PolarBurstSR functions as a benchmark for burst super-resolution in polarization images. These datasets, collected under various real-world conditions, enable comprehensive evaluation. Additionally, we present a model for analyzing polarization noise to quantify noise propagation, tested on a large dataset captured in a darkroom environment. As part of our application, we compare the latest burst super-resolution models, highlighting the advantages of training tailored to polarization compared to RGB-based methods. This work establishes a benchmark for polarization burst super-resolution and offers critical insights into noise propagation, thereby enhancing polarization image reconstruction.

Problem

• Lack of tailored datasets for polarization burst super-resolution
• Low light efficiency and resolution in polarization imaging
• Challenges in noise analysis for polarization measurements

Innovation

• Introduces PolarNS for polarization noise statistics
• Develops PolarBurstSR for burst super-resolution benchmarking
• Proposes noise propagation model for polarization imaging