Cryo-SWAN: the Multi-Scale Wavelet-decomposition-inspired Autoencoder Network for molecular density representation of molecular volumes

• URL: http://arxiv.org/abs/2603.03342v1
• Date: Wed, 18 Feb 2026 18:05:08 GMT
• Title: Cryo-SWAN: the Multi-Scale Wavelet-decomposition-inspired Autoencoder Network for molecular density representation of molecular volumes
• Abstract summary: Cryo-SWAN is a voxel-based variational autoencoder inspired by multi-scale wavelet decomposition.<n>It consistently improves reconstruction quality over state-of-the-art 3D autoencoders.
• Score: 5.24224690492277
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis [33.836541706312055]
  High-fidelity 3D MRI synthesis requires both globally coherent anatomy and fine-grained voxel-level detail.<n>We present VoxStruct3D, a voxel-space flow-matching framework that directly models full-resolution MRI volumes.<n> Experiments on pathological and healthy T1-weighted brain MRI datasets show that VoxStruct3D achieves the strongest overall performance.
  arXiv  Detail & Related papers  (2026-08-05T07:51:35Z)
• CryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models [20.31346781705925]
  We present CryoLVM, a foundation model that learns rich structural representations from experimental density maps with resolved structures.<n>We demonstrate CryoLVM's effectiveness across three critical cryo-EM tasks: density map sharpening, density map super-resolution, and missing wedge restoration.
  arXiv  Detail & Related papers  (2026-02-02T13:36:36Z)
• Diffusion Model-Based Data Augmentation for Enhanced Neuron Segmentation [7.83854380301501]
  Current deep learning-based methods are limited by their reliance on large-scale training data and extensive, time-consuming manual annotations.<n>We propose a diffusion-based data augmentation framework capable of generating diverse and structurally plausible image-label pairs.<n>Our method improves the ARAND metric by 32.1% and 30.7%, respectively, when combined with two different post-processing methods.
  arXiv  Detail & Related papers  (2026-01-22T09:12:05Z)
• CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction [48.45613121595709]
  cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution.<n>The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations.<n>We propose cryoSplat, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation.
  arXiv  Detail & Related papers  (2025-08-06T23:24:43Z)
• Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshes [1.573038298640368]
  3D Geometric Mesh Network (3DGeoMeshNet), is a novel GCN-based framework that uses anisotropic convolution layers to learn both global and local features directly in the spatial domain.<n>Our architecture features a multi-scale encoder-decoder structure, where separate global and local pathways capture both large-scale geometric structures and fine-grained local details.
  arXiv  Detail & Related papers  (2025-07-07T07:36:03Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra [60.39311767532607]
  We present DiffMS, a formula-restricted encoder-decoder generative network that achieves state-of-the-art performance on this task.<n>To develop a robust decoder that bridges latent embeddings and molecular structures, we pretrain the diffusion decoder with fingerprint-structure pairs.<n>Experiments on established benchmarks show that DiffMS outperforms existing models on de novo molecule generation.
  arXiv  Detail & Related papers  (2025-02-13T18:29:48Z)
• Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks [58.050130177241186]
  Noise perturbations often corrupt 3-D point clouds, hindering downstream tasks such as surface reconstruction, rendering, and further processing. This paper introduces finegranularity dynamic graph convolutional networks called GDGCN, a novel approach to denoising in 3-D point clouds.
  arXiv  Detail & Related papers  (2024-11-21T14:19:32Z)
• Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis [70.40950409274312]
  We modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. We also develop a fusion-based meshing strategy followed by mesh simplification and appearance model fitting. The compact meshes produced by our model can be rendered in real-time on mobile devices.
  arXiv  Detail & Related papers  (2024-02-19T18:59:41Z)
• CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations [49.49939711956354]
  Cryo-electron microscopy (cryo-EM) allows for the high-resolution reconstruction of 3D structures of proteins and other biomolecules. It is still challenging to reconstruct the continuous motions of 3D structures from noisy and randomly oriented 2D cryo-EM images. We propose CryoFormer, a new approach for continuous heterogeneous cryo-EM reconstruction.
  arXiv  Detail & Related papers  (2023-03-28T18:59:17Z)
• CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images [30.738209997049395]
  We introduce cryoAI, an ab initio reconstruction algorithm for homogeneous conformations that uses gradient-based optimization of particle poses and the electron scattering potential from single-particle cryo-EM data. CryoAI achieves results on par with state-of-the-art cryo-EM solvers for both simulated and experimental data, one order of magnitude faster for large datasets and with significantly lower memory requirements than existing methods.
  arXiv  Detail & Related papers  (2022-03-15T17:58:03Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.