牛哥精选 · 三个月

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv AI 2026-05-20

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

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…

归一化等变性图像去噪分布偏移骨干网络结构先验

🤖 AI·大模型 arXiv 计算机视觉 2026-05-20

Adaptive double-phase Rudin--Osher--Fatemi denoising model

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…

图像去噪 rof模型自适应双阶段数学建模

📝 深度技术 arXiv 计算机视觉 2026-05-19

Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning

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…

残差噪声学习跨剂量pet去噪低剂量pet 图像去噪深度学习

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

Adaptive double-phase Rudin--Osher--Fatemi denoising model

Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning

📅 日期