Thermal Image Processing via Physics-Inspired Deep Networks
This addresses thermal image quality issues for computer vision applications, offering a practical solution without requiring training data or calibration.
The paper tackles thermal image processing by introducing DeepIR, a framework that combines physics-based sensor modeling with deep network regularization, achieving a 10dB PSNR improvement in non-uniformity correction with as few as three images.
We introduce DeepIR, a new thermal image processing framework that combines physically accurate sensor modeling with deep network-based image representation. Our key enabling observations are that the images captured by thermal sensors can be factored into slowly changing, scene-independent sensor non-uniformities (that can be accurately modeled using physics) and a scene-specific radiance flux (that is well-represented using a deep network-based regularizer). DeepIR requires neither training data nor periodic ground-truth calibration with a known black body target--making it well suited for practical computer vision tasks. We demonstrate the power of going DeepIR by developing new denoising and super-resolution algorithms that exploit multiple images of the scene captured with camera jitter. Simulated and real data experiments demonstrate that DeepIR can perform high-quality non-uniformity correction with as few as three images, achieving a 10dB PSNR improvement over competing approaches.