# TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization

arXiv: https://arxiv.org/abs/2508.03727 · HTML: https://mlsanity.com/paper/2508.03727/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images](https://mlsanity.com/paper/2101.02824/) (2021)
- [Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing](https://mlsanity.com/paper/1805.05308/) (2018)
- [Thermal Image Processing via Physics-Inspired Deep Networks](https://mlsanity.com/paper/2108.07973/) (2021)
- [A Multi-spectral Dataset for Evaluating Motion Estimation Systems](https://mlsanity.com/paper/2007.00622/) (2020)
- [Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image](https://mlsanity.com/paper/2405.15395/) (2024)
- [DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging](https://mlsanity.com/paper/2503.00905/) (2025)
- [OdomBeyondVision: An Indoor Multi-modal Multi-platform Odometry Dataset Beyond the Visible Spectrum](https://mlsanity.com/paper/2206.01589/) (2022)

## Built on by (most cited first, 1 of 1)

- [TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index](https://mlsanity.com/paper/2606.19813/) (2026)

## Abstract (arXiv)

Thermal infrared imaging exhibits considerable potentials for robotic perception tasks, especially in environments with poor visibility or challenging lighting conditions. However, TIR images typically suffer from heavy non-uniform fixed-pattern noise, complicating tasks such as object detection, localization, and mapping. To address this, we propose a diffusion-based TIR image denoising framework leveraging latent-space representations and wavelet-domain optimization. Utilizing a pretrained stable diffusion model, our method fine-tunes the model via a novel loss function combining latent-space and discrete wavelet transform (DWT) / dual-tree complex wavelet transform (DTCWT) losses. Additionally, we implement a cascaded refinement stage to enhance fine details, ensuring high-fidelity denoising results. Experiments on benchmark datasets demonstrate superior performance of our approach compared to state-of-the-art denoising methods. Furthermore, our method exhibits robust zero-shot generalization to diverse and challenging real-world TIR datasets, underscoring its effectiveness for practical robotic deployment.