AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Stokes-Informed Diffusion for Robust Linear Polarization Estimation

Yidong Luo, Chenggong Li, Yuchao Feng, Boxin Shi, Junchao Zhang, Xin Yuan

ECCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Stage-II end-to-end LoRA adaptation of VAE encoder (ablation)GenPolar · RLP testDoLP PSNR: 28.49 -> 29.54Improved
add Stage-II end-to-end LoRA adaptation of VAE encoder (ablation)GenPolar · RLP testAoP MeanAE: 23.12 -> 20.15Improved
pre-adapt VAE encoder with LoRA via reconstruction only (ablation)GenPolar · RLP testDoLP PSNR: 28.49 -> 27.92Hurt
pre-adapt VAE encoder with LoRA via reconstruction only (ablation)GenPolar · RLP testAoP MeanAE: 23.12 -> 23.49Hurt
pre-adapt VAE encoder with LoRA via reconstruction only (ablation)VAE reconstruction · RLP testVAE DoLP mean abs error: 0.081 -> 0.035Improved
insert LoRA into VAE encoder during Stage-I multi-step training (ablation)GenPolar Stage I · RLP testAoPHurt
distill to one-step generator with LoRA instead of without LoRA (ablation)GenPolar · RLP testAoP MeanAEImproved
replace end-to-end regression with diffusion sampling (ablation)GenPolar · RLP testDoLP/AoPImproved
add observability-aware AoP loss (tau_train 0.05) (ablation)GenPolar · RLP testAoPImproved
predict channel-wise Stokes instead of gray-averaged Stokes (ablation)GenPolar · RLP testpolarization cuesImproved
predict Stokes (S1,S2) instead of direct DoLP and sin/cos 2AoP (ablation)GenPolar · RLP testDoLP/AoPImproved
use GenPolar instead of MAEpolarization estimation · RSP testAoP MeanAE: 33.51 -> 27.60Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy