TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization
By: Tai Hyoung Rhee, Dong-guw Lee, Ayoung Kim
Potential Business Impact:
Cleans up blurry heat pictures for robots.
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.
Similar Papers
Inference-Time Scaling of Diffusion Models for Infrared Data Generation
CV and Pattern Recognition
Makes AI create better "night vision" pictures.
TDiff: Thermal Plug-And-Play Prior with Patch-Based Diffusion
CV and Pattern Recognition
Improves blurry, noisy thermal camera pictures.
Contrast-Guided Cross-Modal Distillation for Thermal Object Detection
CV and Pattern Recognition
Improves night vision cameras to see better.