Long-range Turbulence Mitigation: A Large-scale Dataset and A Coarse-to-fine Framework

TL;DR

This paper introduces a large-scale long-range atmospheric turbulence dataset and proposes a coarse-to-fine framework that combines dynamic and static priors to effectively mitigate severe distortions in long-range imaging.

Contribution

The work presents a new dataset RLR-AT for long-range turbulence and a novel coarse-to-fine framework that improves distortion mitigation by leveraging dynamic and static scene priors.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Effectively reduces severe geometric distortions in long-range images.

Demonstrates robustness across diverse scenes and distances.

Abstract

Long-range imaging inevitably suffers from atmospheric turbulence with severe geometric distortions due to random refraction of light. The further the distance, the more severe the disturbance. Despite existing research has achieved great progress in tackling short-range turbulence, there is less attention paid to long-range turbulence with significant distortions. To address this dilemma and advance the field, we construct a large-scale real long-range atmospheric turbulence dataset (RLR-AT), including 1500 turbulence sequences spanning distances from 1 Km to 13 Km. The advantages of RLR-AT compared to existing ones: turbulence with longer-distances and higher-diversity, scenes with greater-variety and larger-scale. Moreover, most existing work adopts either registration-based or decomposition-based methods to address distortions through one-step mitigation. However, they fail to effectively handle long-range turbulence due to its significant pixel displacements. In this work, we propose a coarse-to-fine framework to handle severe distortions, which cooperates dynamic turbulence and static background priors (CDSP). On the one hand, we discover the pixel motion statistical prior of turbulence, and propose a frequency-aware reference frame for better large-scale distortion registration, greatly reducing the burden of refinement. On the other hand, we take advantage of the static prior of background, and propose a subspace-based low-rank tensor refinement model to eliminate the misalignments inevitably left by registration while well preserving details. The dynamic and static priors complement to each other, facilitating us to progressively mitigate long-range turbulence with severe distortions. Extensive experiments demonstrate that the proposed method outperforms SOTA methods on different datasets.