MambaReg: Mamba-Based Disentangled Convolutional Sparse Coding for Unsupervised Deformable Multi-Modal Image Registration 3 Nov 2024 · Kaiang Wen, Bin Xie, Bin Duan, Yan Yan · Edit social preview Precise alignment of multi-modal images with inherent feature discrepancies poses a pivotal challenge ...
2. 研究“disentangled convolutional sparse coding”的原理及应用 解耦卷积稀疏编码是一种将图像特征分解为多个独立且可解释的成分的技术。它通过卷积稀疏编码方法,将图像表示为一组稀疏的、解耦的卷积核的组合。这种方法能够有效地提取图像中的关键特征,同时保持这些特征之间的独立性,有助于理解和分析图像内容。 3. ...
Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 40(4):834–848, 2017. 1 [3] Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Re...