HATIR: 用于湍流红外视频超分辨率的热感知扩散
HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution
AI总结:
HATIR通过热感知变形先验联合建模湍流退化与结构细节损失,提出相位引导流估计器和湍流感知解码器,构建首个湍流红外视频超分辨率数据集FLIR-IVSR,提升非均匀退化下的结构恢复精度。
摘要:
红外视频在恶劣环境中具有重要应用价值,但常受严重大气湍流和压缩退化影响。现有视频超分辨率方法要么忽视红外与可见图像之间的固有模态差异,要么无法恢复湍流引起的失真。直接将湍流抑制(TM)算法与超分辨率(VSR)方法串联会导致误差传播和累积,因为湍流与分辨率退化的建模是解耦的。我们引入HATIR,一种用于湍流红外视频超分辨率的热感知扩散方法,将热感知变形先验注入扩散采样路径,联合建模湍流退化的逆过程和结构细节损失。具体而言,HATIR构建了基于物理原理的相位引导流估计器,利用热活跃区域在时间上具有一致相位响应的特性,使可靠湍流感知的流引导反向扩散过程。为确保非均匀退化下的结构恢复保真度,提出湍流感知解码器,通过湍流门控和结构感知注意力机制选择性抑制不稳定的时间线索并增强边缘感知的特征聚合。我们构建了FLIR-IVSR数据集,包含来自FLIR T1050sc相机(1024 X 768)的640种不同场景的配对LR-HR序列,涵盖不同相机和物体运动条件。这促进了未来红外视频超分辨率研究。项目页面:https://github.com/JZ0606/HATIR
英文摘要:
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
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。