Stokes-Informed Diffusion for Robust Linear Polarization Estimation

• URL: http://arxiv.org/abs/2607.21239v1
• Date: Thu, 23 Jul 2026 11:56:15 GMT
• Title: Stokes-Informed Diffusion for Robust Linear Polarization Estimation
• Abstract summary: GenPolar is a Stokes-informed diffusion framework grounded in the Mueller formalism from an intensity observation.<n>It achieves state-of-the-art performance in both DoLP fidelity and AoP stability.<n>These improvements translate to significant and consistent gains in downstream applications, including material detection and de-reflection.
• Score: 49.459667092743445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Polarization cues benefit applications such as material detection and de-reflection, yet acquiring them typically requires dedicated hardware. This motivates us to estimate the linear polarization from a single RGB image. However, the task is inherently ill-posed, with the Angle of Polarization (AoP) becoming particularly unstable in weak polarization regions, where the polarimetric signal is overwhelmed by noise, leading to erratic angle estimates. To address these limitations, we propose GenPolar, a Stokes-informed diffusion framework grounded in the Mueller formalism from an intensity observation. Specifically, GenPolar predicts channel-wise linear Stokes components (S1,S2) from intensity S0, from which degree of linear polarization (DoLP) and AoP are analytically derived; AoP is further supervised with an observability-aware loss. In addition, to enable efficient and high-fidelity inference, we adopt a two-stage training strategy. Firstly, a multi-step conditional diffusion model is trained with a physics-based loss. Subsequently, we distill it into a one-step generator, which further supports stable Low-Rank Adaptation (LoRA) of the VAE encoder to mitigate domain-specific autoencoding bias. Extensive experiments across rotating-polarizer, division-of-focal-plane, and hybrid datasets demonstrate that GenPolar achieves state-of-the-art performance in both DoLP fidelity and AoP stability. Crucially, these improvements translate to significant and consistent gains in downstream applications, including material detection and de-reflection.

Related papers

• DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision [8.673131921192995]
  We introduce DensePol, a high-redundancy RGB--polarization dataset based on Division-of-Time (DoT) acquisition.<n>Dense angular sampling substantially improves polarization stability, reducing AoLP deviation from $13.36circ$ to $2.21circ$.<n>Experiments demonstrate improved polarization prediction and downstream surface-normal estimation.
  arXiv  Detail & Related papers  (2026-09-08T18:48:33Z)
• A projection-free approach toward mapping the structured polarization fields [7.927860906142733]
  We present a projection-free method for mapping two-dimensional polarization distributions using Hong-Ou -Mandel interference.<n>Our approach overcomes limitations by exploiting the sensitivity of two-photon bunching to polarization indistinguishability at a balanced beam splitter.<n>The proposed quantum-optical technique offers a simple, scalable, and high-precision framework for characterizing structured polarization fields in birefringent materials.
  arXiv  Detail & Related papers  (2026-07-18T07:05:43Z)
• Differentiable Polarized Path Tracing [60.271569691679794]
  Physically based differentiable rendering has proven to be a powerful tool for inverse rendering problems.<n>We propose a robust, polarization-aware differentiable path tracing method.<n>This formulation enables efficient and stable optimization of material and lighting parameters in complex scenes.
  arXiv  Detail & Related papers  (2026-07-14T20:58:08Z)
• SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation [64.33799467286265]
  Low-Rank Adaptation (LoRA) enables efficient adaptation of large pre-trained models to downstream tasks.<n>We show that when a full fine-tuning gradient is backpropagated to the low-rank matrices, it undergoes anisotropic scaling driven by their singular values.<n>We propose a new low-rank parameterization, SDS-LoRA, which structurally decouples singular values from the backward pass.
  arXiv  Detail & Related papers  (2026-06-15T09:27:50Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction [42.44037120162351]
  Polarimetric imaging captures surface polarization characteristics, such as the Degree of Linear Polarization (DoLP) and the Angle of Polarization (AoP)<n>Existing Division of-Focal-Plane (DoFP) cameras face hardware bottlenecks and often cannot support high-frame-rate acquisition.<n>We propose the first space-time polarization video reconstruction architecture.
  arXiv  Detail & Related papers  (2026-05-11T09:33:50Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• Conditional Polarization Guidance for Camouflaged Object Detection [5.146223292969599]
  We propose an asymmetric RGB-polarization framework to regulate RGB feature learning for camouflaged object detection.<n>Unlike conventional feature fusion strategies, the proposed conditional guidance mechanism dynamically modulates RGB features using polarization priors.<n>We also introduce a polarization edge-guided frequency refinement strategy that enhances high-frequency components under polarization constraints.
  arXiv  Detail & Related papers  (2026-03-31T17:03:06Z)
• Continuous Automatic Polarization Channel Stabilization from Heterodyne Detection of Coexisting Dim Reference Signals [5.602886645159814]
  Quantum networking continues to encode information in polarization states due to ease and precision. variable environmental polarization transformations induced by deployed fiber need correction for deployed quantum networking. We present a new method for automatic polarization compensation ( APC) and demonstrate its performance on a metropolitan quantum network.
  arXiv  Detail & Related papers  (2024-11-22T18:58:01Z)
• PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection [81.16859686137435]
  We present PARTNER, a novel 3D object detector in the polar coordinate. Our method outperforms the previous polar-based works with remarkable margins of 3.68% and 9.15% on and ONCE validation set.
  arXiv  Detail & Related papers  (2023-08-08T01:59:20Z)

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.