Cryo-SWAN: 多尺度小波分解启发的自编码网络用于分子密度的分子体积表示
Cryo-SWAN: the Multi-Scale Wavelet-decomposition-inspired Autoencoder Network for molecular density representation of molecular volumes
AI总结：
Cryo-SWAN通过多尺度小波分解启发的自编码网络，实现分子密度体积的鲁棒表示，提升3D重建和生成质量。
摘要：
从体素化数据中学习鲁棒的3D形状表示对于推动生物医学影像中的AI方法至关重要。然而，大多数现代3D计算机视觉方法都基于点云、网格或八叉树，而体积密度图，结构生物学和冷冻电镜的原生格式，仍相对被忽视。我们提出了Cryo-SWAN，一种基于体素的变分自编码器，灵感来自多尺度小波分解。该模型在感知尺度上进行条件粗到细的潜在编码和递归残差量化，能够准确捕捉分子密度体积中的全局几何和高频结构细节。在ModelNet40、BuildingNet和新编纂的冷冻电镜体积数据集ProteinNet3D上进行评估，Cryo-SWAN在重建质量上始终优于最先进的3D自编码器。我们证明分子密度在学习的潜在空间中根据共享的几何特征组织，而与扩散模型的结合能够实现去噪和条件形状生成。共同，Cryo-SWAN是数据驱动的结构生物学和体积成像的实用框架。
英文摘要：
Learning robust representations of 3D shapes from voxelized data is essential for advancing AI methods in biomedical imaging. However, most contemporary 3D computer vision approaches operate on point clouds, meshes, or octrees, while volumetric density maps, the native format of structural biology and cryo-EM, remain comparatively underexplored. We present Cryo-SWAN, a voxel-based variational autoencoder inspired by multi-scale wavelet decomposition. The model performs conditional coarse-to-fine latent encoding and recursive residual quantization across perception scales, enabling accurate capture of both global geometry and high-frequency structural detail in molecular density volumes. Evaluated on ModelNet40, BuildingNet, and a newly curated dataset of cryo-EM volumes, ProteinNet3D, Cryo-SWAN consistently improves reconstruction quality over state-of-the-art 3D autoencoders. We demonstrate that the molecular densities organize in learned latent space according to shared geometric features, while integration with diffusion models enables denoising and conditional shape generation. Together, Cryo-SWAN is a practical framework for data-driven structural biology and volumetric imaging.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
