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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rhee, Tai Hyoung, Lee, Dong-guw, Kim, Ayoung
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908479667568640
author Rhee, Tai Hyoung
Lee, Dong-guw
Kim, Ayoung
author_facet Rhee, Tai Hyoung
Lee, Dong-guw
Kim, Ayoung
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03727
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization
Rhee, Tai Hyoung
Lee, Dong-guw
Kim, Ayoung
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
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.
title TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
url https://arxiv.org/abs/2508.03727