Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

2026-03-01

AI Summary

This work addresses the limitations of existing atmospheric turbulence synthesis methods, which oversimplify the relationship between exposure time and blur, leading to distorted synthetic data and poor model generalization. To overcome this, the study introduces the first physically accurate turbulence blur synthesis framework by modeling exposure time as a continuous variable. It proposes an exposure-time-dependent modulation transfer function (ET-MTF), from which an tilt-invariant point spread function (PSF) is derived. This PSF is further integrated with a spatially varying blur width field to generate realistic turbulence effects. Based on this approach, the authors construct ET-Turb, the first large-scale turbulence video dataset explicitly incorporating continuous exposure times, comprising 5,083 videos. Models trained on ET-Turb demonstrate significantly improved realism and generalization when restoring real-world turbulent imagery.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Atmospheric turbulence significantly degrades long-range imaging by introducing geometric warping and exposure-time-dependent blur, which adversely affects both visual quality and the performance of high-level vision tasks. Existing methods for synthesizing turbulence effects often oversimplify the relationship between blur and exposure-time, typically assuming fixed or binary exposure settings. This leads to unrealistic synthetic data and limited generalization capability of trained models. To address this gap, we revisit the modulation transfer function (MTF) formulation and propose a novel Exposure-Time-dependent MTF (ET-MTF) that models blur as a continuous function of exposure-time. For blur synthesis, we derive a tilt-invariant point spread function (PSF) from the ET-MTF, which, when integrated with a spatially varying blur-width field, provides a comprehensive and physically accurate characterization of turbulence-induced blur. Building on this synthesis pipeline, we construct ET-Turb, a large-scale synthetic turbulence dataset that explicitly incorporates continuous exposure-time modeling across diverse optical and atmospheric conditions. The dataset comprises 5,083 videos (2,005,835 frames), partitioned into 3,988 training and 1,095 test videos. Extensive experiments demonstrate that models trained on ET-Turb produce more realistic restorations and achieve superior generalization on real-world turbulence data compared to those trained on other datasets. The dataset is publicly available at: github.com/Jun-Wei-Zeng/ET-Turb.

Problem

• atmospheric turbulence
• exposure-time
• blur synthesis
• realistic image degradation
• synthetic dataset

Innovation

• Exposure-Time-dependent MTF
• Atmospheric Turbulence Synthesis
• Continuous Blur Modeling
• Tilt-invariant PSF
• ET-Turb Dataset