# Learning Polarization Image Restoration with General Restoration Priors

arXiv: https://arxiv.org/abs/2609.30728 · HTML: https://mlsanity.com/paper/2609.30728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [PixelDiT: Pixel Diffusion Transformers for Image Generation](https://mlsanity.com/paper/2511.20645/) (2025)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [Deep Polarization Imaging for 3D shape and SVBRDF Acquisition](https://mlsanity.com/paper/2105.02875/) (2021)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [PolarFree: Polarization-based Reflection-free Imaging](https://mlsanity.com/paper/2503.18055/) (2025)
- [Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation](https://mlsanity.com/paper/2007.14292/) (2020)
- [PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution](https://mlsanity.com/paper/2504.07758/) (2025)
- [Two-Step Color-Polarization Demosaicking Network](https://mlsanity.com/paper/2209.06027/) (2022)
- [FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model](https://mlsanity.com/paper/2512.09282/) (2025)
- [ShareCMP: Polarization-Aware RGB-P Semantic Segmentation](https://mlsanity.com/paper/2312.03430/) (2023)
- [Learning to Deblur Polarized Images](https://mlsanity.com/paper/2402.18134/) (2024)
- [Polarization Denoising and Demosaicking: Dataset and Baseline Method](https://mlsanity.com/paper/2509.10098/) (2025)
- [Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking](https://mlsanity.com/paper/2602.23847/) (2026)
- [Stokes-Informed Diffusion for Robust Linear Polarization Estimation](https://mlsanity.com/paper/2607.21239/) (2026)
- [Architectural Unification for Polarimetric Imaging Across Multiple Degradations](https://mlsanity.com/paper/2603.05834/) (2026)
- [PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications](https://mlsanity.com/paper/2603.23071/) (2026)
- [PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction](https://mlsanity.com/paper/2605.10275/) (2026)

## Abstract (arXiv)

Polarization imaging captures distinctive surface and geometric cues that benefit a wide range of vision tasks. However, real-world polarization acquisition is often affected by multiple coupled degradations, making image restoration essential for practical polarization vision. Existing methods are largely tailored to specific degradations and remain constrained by the limited scale and quality of polarization data. To address these limitations, we develop an all-in-one polarization restoration framework for diverse and composite degradations. We first study the impact of different polarization representations on restoration performance and identify the normalized Stokes representation as an effective choice for separating intensity and polarization information. Accordingly, we devise a dual-branch architecture that separates intensity and polarization modeling. To overcome the limitations of polarization-specific training, the intensity branch leverages pretrained general restoration priors and a mixture-of-experts extension for composite degradations, while its restoration knowledge is adaptively distilled into the symmetric polarization branch via a cross-domain feature transform. In addition, we establish a composite-degradation polarization benchmark to support all-in-one restoration research. Extensive experiments on public datasets and our proposed benchmark demonstrate the effectiveness of the proposed method.