Article

An Integrated Framework of Frequency-Domain Denoising with Learnable Parameters in Variational Autoencoders

2026-01-06

Abstract excerpt

<title>Abstract</title> <p>Variational Autoencoders (VAEs) have demonstrated substantial utility in generative modeling, however their performance is often compromised when inputs are corrupted by noise or measurement artifacts. Traditional approaches to preprocessing either fail to adapt to spatially heterogeneous noise or result in excessive smoothing of high-frequency features. In this study, we propose an aut...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8f1e1b89-6494-559a-8a93-7e972d70c2d8
DOI: 10.21203/rs.3.rs-8209010/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

An Integrated Framework of Frequency-Domain Denoising with Learnable Parameters in Variational AutoencodersDOI 10.21203/rs.3.rs-8209010/v1Read

A Lightweight Perceptual-Guided VQVAE for High-Fidelity Image CompressionSemantic proximity Read

Neural Steered Mixture of Experts for Medical Image Denoising, and Super-ResolutionSemantic proximity Read

Variational decomposition autoencoding improves disentanglement of latent representationsSemantic proximity Read

A Systematic Review of Wavelet-Based Pooling for Enhancing GANs: Central Trends, Auxiliary Pooling Strategies, and Complementary Wavelet IntegrationsSemantic proximity Read

MFDRNet: A Self-Supervised Framework for Sparse-View XACT Image Reconstruction via Multi-View Fusion and Artifact DisentanglementSemantic proximity Read

Quality-preserving low-cost probabilistic 3D denoising with applications to Computed TomographySemantic proximity Read

Residual Diffusion with Adaptive Data Consistency for Sparse-View CT ReconstructionSemantic proximity Read

Parameter Efficient Fine-tuning of Transformer-based Masked Autoencoder Enhances Resource Constrained Neuroimage AnalysisSemantic proximity Read

VMDiff: A novel hybrid CNN-Mamba generative framework for retinal phenotype image enhancement.Semantic proximity Read

High-fidelity fast volumetric brain MRI using synergistic wave-controlled aliasing in parallel imaging and a hybrid denoising generative adversarial networkSemantic proximity Read

Medical Image Generation using Denoising Diffusion Probabilistic ModelSemantic proximity Read

MedSAM-prior-guided coarse-to-fine CBCT synthesis from ZTE MRISemantic proximity Read