Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking

• URL: http://arxiv.org/abs/2602.23847v1
• Date: Fri, 27 Feb 2026 09:39:07 GMT
• Title: Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking
• Authors: Chenggong Li, Yidong Luo, Junchao Zhang, Degui Yang,
• Abstract summary: CPDM aims to reconstruct full-resolution polarization images of four directions from the color-polarization filter array (CPFA) raw image.<n>We introduce the image diffusion prior from text-to-image (T2I) models to overcome the performance bottleneck of network-based methods.
• Score: 3.5335358134182937
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Color polarization demosaicking (CPDM) aims to reconstruct full-resolution polarization images of four directions from the color-polarization filter array (CPFA) raw image. Due to the challenge of predicting numerous missing pixels and the scarcity of high-quality training data, existing network-based methods, despite effectively recovering scene intensity information, still exhibit significant errors in reconstructing polarization characteristics (degree of polarization, DOP, and angle of polarization, AOP). To address this problem, we introduce the image diffusion prior from text-to-image (T2I) models to overcome the performance bottleneck of network-based methods, with the additional diffusion prior compensating for limited representational capacity caused by restricted data distribution. To effectively leverage the diffusion prior, we explicitly model the polarization uncertainty during reconstruction and use uncertainty to guide the diffusion model in recovering high error regions. Extensive experiments demonstrate that the proposed method accurately recovers scene polarization characteristics with both high fidelity and strong visual perception.

Related papers

• PolarAnything: Diffusion-based Polarimetric Image Synthesis [59.14294818211059]
  We propose PolarAnything, capable of synthesizing polarization images from a single RGB input with both photorealism and physical accuracy.<n>Experiments show that our model generates high-quality polarization images and supports downstream tasks like shape from polarization.
  arXiv  Detail & Related papers  (2025-07-23T07:09:10Z)
• Shape from Polarization of Thermal Emission and Reflection [2.7317088388886384]
  We leverage the Shape from Polarization (SfP) technique in the Long-Wave Infrared (LWIR) spectrum, where most materials are opaque and emissive.<n>We formulated a polarization model that explicitly accounts for the combined effects of emission and reflection.<n>We implemented a prototype system and created ThermoPol, the first real-world benchmark dataset for LWIR SfP.
  arXiv  Detail & Related papers  (2025-06-23T00:33:17Z)
• PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution [63.87900679891159]
  The resolution of a polarization camera is often much lower than that of a conventional RGB camera.<n>Existing polarized image demosaicing (PID) methods are limited in that they cannot enhance resolution.<n>We propose PIDSR, a joint framework that performs complementary Polarized Image Demosaicing and Super-Resolution.
  arXiv  Detail & Related papers  (2025-04-10T13:56:33Z)
• Glossy Object Reconstruction with Cost-effective Polarized Acquisition [41.96986483856648]
  This work introduces a scalable polarization-aided approach that employs cost-effective acquisition tools.<n>The proposed approach represents polarimetric BRDF, Stokes vectors, and polarization states of object surfaces as neural implicit fields.<n>By leveraging fundamental physical principles for the implicit representation of polarization rendering, our method demonstrates superiority over existing techniques.
  arXiv  Detail & Related papers  (2025-04-09T16:38:51Z)
• Diffusion-based Virtual Staining from Polarimetric Mueller Matrix Imaging [8.016374085889172]
  We propose a Regulated Bridge Diffusion Model (RBDM) for polarization-based virtual staining.<n>RBDM learns the mapping from polarization images to other modalities such as H&E and fluorescence.<n>Experiment results show that our model greatly outperforms other benchmark methods.
  arXiv  Detail & Related papers  (2025-03-03T09:45:27Z)
• Video Frame Interpolation for Polarization via Swin-Transformer [9.10220649654041]
  Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored. This study proposes a multi-stage and multi-scale network called Swin-VFI based on the Swin-Transformer. Experimental results demonstrate our approach's superior reconstruction accuracy across all tasks.
  arXiv  Detail & Related papers  (2024-06-17T09:48:54Z)
• Learning to Deblur Polarized Images [59.33932533761383]
  A polarization camera can capture four linear polarized images with different polarizer angles in a single shot.<n>Since the on-chip micro-polarizers block part of the light so that the sensor often requires a longer exposure time, the captured polarized images are prone to motion blur.<n>We propose a polarized image deblurring pipeline to solve the problem in a polarization-aware manner.
  arXiv  Detail & Related papers  (2024-02-28T07:56:28Z)
• Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data [51.95347650131366]
  6D pose estimation pipelines that rely on RGB-only or RGB-D data show limitations for photometrically challenging objects. A supervised learning-based method utilising complementary polarisation information is proposed to overcome such limitations.
  arXiv  Detail & Related papers  (2023-08-21T10:56:00Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization [67.99082021804145]
  We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss) DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models.
  arXiv  Detail & Related papers  (2022-01-04T08:30:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.