Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence

TL;DR

This paper introduces PPTRN, a novel image restoration method combining diffusion-based priors and Transformer features to effectively remove atmospheric turbulence distortions, outperforming existing techniques.

Contribution

The paper presents a new two-stage framework with a probabilistic prior driven cross attention mechanism, enhancing turbulence image restoration by integrating diffusion models with Transformers.

Findings

Significantly improves image clarity and structural fidelity.

Sets a new benchmark in turbulence image restoration.

Effectively reduces artifacts and enhances spatial coherence.

Abstract

Atmospheric turbulence introduces severe spatial and geometric distortions, challenging traditional image restoration methods. We propose the Probabilistic Prior Turbulence Removal Network (PPTRN), which combines probabilistic diffusion-based prior modeling with Transformer-driven feature extraction to address this issue. PPTRN employs a two-stage approach: first, a latent encoder and Transformer are jointly trained on clear images to establish robust feature representations. Then, a Denoising Diffusion Probabilistic Model (DDPM) models prior distributions over latent vectors, guiding the Transformer in capturing diverse feature variations essential for restoration. A key innovation in PPTRN is the Probabilistic Prior Driven Cross Attention mechanism, which integrates the DDPM-generated prior with feature embeddings to reduce artifacts and enhance spatial coherence. Extensive experiments validate that PPTRN significantly improves restoration quality on turbulence-degraded images, setting a new benchmark in clarity and structural fidelity.