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

TL;DR

This paper introduces a diffusion-based denoising framework for thermal infrared images that leverages latent-space and wavelet domain optimization, achieving superior results and robust generalization for robotic perception tasks.

Contribution

The authors propose a novel TIR image denoising method combining diffusion models with wavelet domain optimization and a cascaded refinement stage, enhancing detail preservation and generalization.

Findings

Outperforms state-of-the-art denoising methods on benchmark datasets.

Exhibits robust zero-shot generalization to real-world TIR data.

Provides high-fidelity denoising suitable for robotic perception.

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.