用扩散模型和小波域优化，有效去除热成像噪声。
TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization
- 结合潜在空间与小波变换设计新损失函数。
- 在多个数据集上优于现有去噪方法，细节保留更好。
- 零样本泛化强，适合实际机器人应用。
热成像在低可见度或复杂光照环境下对机器人感知具有重要潜力，但通常存在严重的非均匀固定模式噪声，影响目标检测、定位和建图等任务。为此，本文提出一种基于扩散模型的热成像去噪框架，利用预训练稳定扩散模型，并通过结合潜在空间损失与离散小波变换（DWT）/双树复小波变换（DTCWT）损失进行微调。此外，引入级联精修阶段以增强细节，实现高保真去噪。在基准数据集上的实验表明，该方法显著优于当前最先进的去噪技术。同时，其在多样且复杂的现实世界热成像数据集上展现出优异的零样本泛化能力，证明了其在实际机器人部署中的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。