TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index

2026-06-18

AI Summary

Indoor thermal infrared images are often degraded by random noise and stripe-like fixed-pattern noise, severely compromising robotic perception tasks. Existing approaches struggle to balance accuracy and efficiency and typically rely on synthetically generated noise for training. This work proposes TIDY, a lightweight wavelet-domain denoising method trained in a supervised manner using the first-ever real-world paired clean–noisy thermal image dataset. By leveraging wavelet transforms to explicitly separate structural content from noise, TIDY innovatively incorporates wavelet entropy and a wavelet directional stripe index into its loss function to suppress random and structured noise, respectively. Operating at 34 Hz, TIDY demonstrates robust performance under severe degradation and zero-shot conditions, significantly enhancing downstream tasks such as thermal-inertial odometry and monocular depth estimation.

Abstract

Thermal infrared (TIR) imaging has been a popular choice for field robotics due to its robust perception capability under low light visual degradation, but it suffers from severe stochastic and fixed-pattern noise that breaks downstream estimation. This noise is intensified indoors due to low thermal contrast and uniform temperature distributions, contributing to the relative lack of indoor TIR deployments. Existing TIR denoising methods exhibit a poor accuracy-efficiency tradeoff, either too slow for online deployment required in robotics or insufficiently robust to severe degradation, while typically being trained on synthetic noise. Addressing these problems, we propose TIDY, a lightweight wavelet-domain denoiser trained on real clean-noisy TIR data. By reformulating TIR denoising in the wavelet domain, TIDY explicitly disentangles noise from structural content, enabling targeted suppression with reduced spatial complexity, significantly improving inference speed over prior methods (~34Hz). TIDY introduces two new metrics, Wavelet Entropy and Wavelet Directional Stripe Index, as complementary loss terms to explicitly suppress stochastic noise and stripe artifacts. Across severe indoor corruption and zero-shot settings, TIDY improves robustness and yields consistent gains in downstream robotics tasks including thermal inertial odometry and monocular depth estimation. Code and dataset is available at: https://github.com/williamrheeth/TIDY

Problem

• Thermal Infrared Image Denoising
• Fixed-Pattern Noise
• Stochastic Noise
• Indoor Thermal Imaging
• Real-World Degradation

Innovation

• Wavelet Domain Denoising
• Thermal Infrared Imaging
• Wavelet Entropy
• Directional Stripe Index
• Real-World TIR Denoising