HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution

TL;DR

HATIR introduces a heat-aware diffusion model that jointly addresses turbulence and resolution degradation in infrared video super-resolution, utilizing physical priors and a new dataset for turbulence-aware infrared VSR.

Contribution

The paper proposes a novel heat-aware diffusion framework with a phasor-guided flow estimator and turbulence-aware decoder, and introduces the FLIR-IVSR dataset for turbulent infrared VSR.

Findings

HATIR effectively models turbulent degradation and structural detail loss.

The method outperforms existing approaches on the FLIR-IVSR dataset.

The dataset provides a new benchmark for infrared VSR under turbulence.

Abstract

Infrared video has been of great interest in visual tasks under challenging environments, but often suffers from severe atmospheric turbulence and compression degradation. Existing video super-resolution (VSR) methods either neglect the inherent modality gap between infrared and visible images or fail to restore turbulence-induced distortions. Directly cascading turbulence mitigation (TM) algorithms with VSR methods leads to error propagation and accumulation due to the decoupled modeling of degradation between turbulence and resolution. We introduce HATIR, a Heat-Aware Diffusion for Turbulent InfraRed Video Super-Resolution, which injects heat-aware deformation priors into the diffusion sampling path to jointly model the inverse process of turbulent degradation and structural detail loss. Specifically, HATIR constructs a Phasor-Guided Flow Estimator, rooted in the physical principle that thermally active regions exhibit consistent phasor responses over time, enabling reliable turbulence-aware flow to guide the reverse diffusion process. To ensure the fidelity of structural recovery under nonuniform distortions, a Turbulence-Aware Decoder is proposed to selectively suppress unstable temporal cues and enhance edge-aware feature aggregation via turbulence gating and structure-aware attention. We built FLIR-IVSR, the first dataset for turbulent infrared VSR, comprising paired LR-HR sequences from a FLIR T1050sc camera (1024 X 768) spanning 640 diverse scenes with varying camera and object motion conditions. This encourages future research in infrared VSR. Project page: https://github.com/JZ0606/HATIR