English

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

Computer Vision and Pattern Recognition 2025-08-07 v1 Robotics Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2508.03727,
  title  = {TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization},
  author = {Tai Hyoung Rhee and Dong-guw Lee and Ayoung Kim},
  journal= {arXiv preprint arXiv:2508.03727},
  year   = {2025}
}

Comments

Accepted at Thermal Infrared in Robotics (TIRO) Workshop, ICRA 2025

R2 v1 2026-07-01T04:35:43.897Z