多智能体协同视觉语言模型，革新PET医学影像去噪新路径
arXiv:2608.13791v1 Announce Type: cross Abstract: Positron emission tomography (PET) imaging suffers from limited spatial resolution and low signal-to…
热红外图像去噪新算法TIDY，巧用小波域熵与方向条纹指数精准消除条纹噪声，计算机视觉方向值得一读的干货论文。
arXiv:2606.19813v1 Announce Type: cross Abstract: Thermal infrared (TIR) imaging has been a popular choice for field robotics due to its robust percep…
提出归一化等变性的结构先验，可应用于任意骨干网络的图像去噪，有效提升分布偏移健壮性。
arXiv:2605.08193v2 Announce Type: replace-cross Abstract: Normalization Equivariance (NE) is a structural prior that improves robustness to distributi…
提出自适应双阶段ROF去噪模型，突破经典方法对非均匀噪声的局限，理论新颖性强
arXiv:2510.04382v2 Announce Type: replace-cross Abstract: Even though more than 30 years have passed since the seminal Rudin--Osher--Fatemi (ROF) pape…
提出残差噪声学习方法，解决PET去噪中跨剂量泛化难题，有效缓解平均效应带来的退化。
arXiv:2604.16925v3 Announce Type: replace Abstract: Cross-dose denoising for low-dose positron emission tomography (LDPET) has been proposed to addres…