# Thermal Image Processing via Physics-Inspired Deep Networks

arXiv: https://arxiv.org/abs/2108.07973 · HTML: https://mlsanity.com/paper/2108.07973/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models](https://mlsanity.com/paper/1703.09912/) (2017)
- [Pixel-Wise Motion Deblurring of Thermal Videos](https://mlsanity.com/paper/2006.04973/) (2020)

## Built on by (most cited first, 9 of 9)

- [Deep Depth Estimation from Thermal Image: Dataset, Benchmark, and Challenges](https://mlsanity.com/paper/2503.22060/) (2025)
- [Foveated Thermal Computational Imaging in the Wild Using All-Silicon Meta-Optics](https://mlsanity.com/paper/2212.06345/) (2022)
- [DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping](https://mlsanity.com/paper/2402.09101/) (2024)
- [TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization](https://mlsanity.com/paper/2508.03727/) (2025)
- [Estimating temperatures with low-cost infrared cameras using deep neural networks](https://mlsanity.com/paper/2307.12130/) (2023)
- [Simultaneous temperature estimation and nonuniformity correction from multiple frames](https://mlsanity.com/paper/2307.12297/) (2023)
- [TDiff: Thermal Plug-And-Play Prior with Patch-Based Diffusion](https://mlsanity.com/paper/2510.06460/) (2025)
- [Thermal is Always Wild: Characterizing and Addressing Challenges in Thermal-Only Novel View Synthesis](https://mlsanity.com/paper/2603.20448/) (2026)
- [TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index](https://mlsanity.com/paper/2606.19813/) (2026)

## Abstract (arXiv)

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.