Denoising Autoencoders

Also known as DAE

Denoising autoencoders learn to reconstruct clean inputs or useful features from corrupted data, helping suppress noise while preserving information needed for later tasks. Common approaches include convolutional reconstruction networks, Noise2Noise training on noisy pairs, and denoising objectives for self-supervised representation learning. They are used for images, spectra, scientific measurements, language, and atomistic data, including settings where clean references or labels are scarce. A central challenge is matching training corruptions to real-world noise: results can depend strongly on the training data, and denoising must preserve subtle signals while generalizing across domains and conditions.

Latest papers

15 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Denoise X: Self-Supervised U-Net for Quantum Mottle Suppression in Chest Radiography
Oct 13, 2026Parth Giramkar, Aryan Patle, Vanita KshirsagarImage Denoising Self-Supervised Image Denoising
Department of Artificial Intelligence and Data Science, Dr. D. Y. Patil Institute of Technology, Pune, Maharashtra 411018, India
Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising
Sep 15, 2026Dingyan Shang, Zhenyu Xu, Youting Wang +2Self-Supervised Image Denoising Denoising Autoencoders
Independent Researcher · Frisco, USA · Fulshear, USA +3
Parameter Estimation of Ringdown Quasinormal Modes with Autoencoder
Sep 13, 2026Momoka Iida, Hayato Motohashi, Hirotaka TakahashiParameter Estimation Gravitational-Wave Astronomy
Graduate School of Integrative Science and Engineering, Tokyo City University, 1-28-1 Tamazutsumi, Setagaya-ku, Tokyo 158-8557, Japan · Research Center for Space Science, Advanced Research Laboratories, Tokyo City University, 1-28-1 Tamazutsumi, Setagaya-ku, Tokyo 158-8557, Japan · Department of Physics, Graduate School of Science, Tokyo Metropolitan University, 1-1 Minami-Osawa, Hachioji, Tokyo 192-0397, Japan +2
CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising
Jul 30, 2026Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand +1Contrastive Learning Denoising Autoencoders
Department of Computer Science and Information Technology Institude for Advanced Studies in Basic Sciences (IASBS) Zanjan, Iran, 45137-66731
Noise-Aware Visual Representation Learning for Medical Visual Question Answering
Jun 4, 2026I Putu Adi Pratama, Bahadorreza Ofoghi, Atul Sajjanhar +1VLM Robustness Denoising Autoencoders
Deakin University, 221 Burwood Highway, Burwood, Victoria 3125, Australia
A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy
May 28, 2026Nisar Nellikunnummel, Andi Barbour, Lutz Wiegart +2Denoising Autoencoders Autoencoders
Brookhaven National Laboratory, Upton, NY 11973, USA · Currently at: Amazon · Currently at: GE Aerospace Research
UNATE: UNsupervised ATomic Embedding for crystal structures property prediction
May 25, 2026Laura Solà-Garcia, Àlex Solé, Javier Ruiz-HidalgoRepresentation Learning Denoising Autoencoders
Signal Theory and Comms. Dept. UPC-Univ. Polit`ecnica de Catalunya Barcelona, Spain
A Practical Noise2Noise Denoising Pipeline for High-Throughput Raman Spectroscopy
May 18, 2026David Martin-Calle, Cesar Alvarez Llamas, Vincent Motto- Ros +3Denoising Autoencoders Convolutional Autoencoder
ILM,UCBL,CNRS · Universit´e Claude Bernard Lyon 1, CNRS, Institut Lumi`ere Mati`ere, F-69622 Villeurbanne, France · ILM,UCBL,CNRS,IUF +1
Attention-Based Chaotic Self-Supervision for Medical Image Classification
May 6, 2026Joao Batista Florindo, Amanda Pontes de Oliveira OrnelasDenoising Autoencoders Self-Supervised Pre-Training
Institute of Mathematics, Statistics and Scientific Computing - University of Campinas, Rua S´ergio Buarque de Holanda, 651, Campinas, Brasil
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
May 2, 2026Mohamed SyDenoising Autoencoders Autoencoders
King Abdullah University of Science and Technology Thuwal, Kingdom of Saudi Arabia
Similarity-Based Bike Station Expansion via Hybrid Denoising Autoencoders
Apr 17, 2026Oluwaleke Yusuf, M. Tsaqif Wismadi, Adil RasheedDenoising Autoencoders Geospatial Representation Learning
Department of Engineering Cybernetics Norwegian University of Science and Technology (NTNU) NO-7491 Trondheim, Norway · Department of Architecture and Planning Norwegian University of Science and Technology (NTNU) NO-7491 Trondheim, Norway
Self-Conditioned Denoising for Atomistic Representation Learning
Mar 17, 2026Tynan Perez, Rafael Gomez-BombarelliSelf-Supervised Learning Molecular Representation Learning
Department of Chemistry, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, 02139, MA, USA · Department of Materials Science and Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, 02139, MA, USA
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
Mar 8, 2026Ruixin Guo, Xinyu Li, Hao Zhou +2Recommender Systems Autoencoders
Kent State University · Auburn University
Efficient reduction of stellar contamination and noise in planetary transmission spectra using neural networks
Feb 10, 2026David S. Duque-Castaño, Lauren Flor-Torres, Jorge I. ZuluagaDenoising Autoencoders Autoencoders
SEAP/FACom, Instituto de Física - FCEN, Universidad de Antioquia, Calle 70 No. 52-21, Medellín, Colombia
Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders
Nov 7, 2025Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini +2Audio Representation Learning Denoising Autoencoders
Johannes Kepler University, Linz, AT · STMS, CNRS, IRCAM, Sorbonne Universit´e, Paris, FR · Queen Mary University, London, UK +1

Oct 13, 2026J/K move · Enter open · S save

Denoise X: Self-Supervised U-Net for Quantum Mottle Suppression in Chest Radiography

Parth Giramkar, Aryan Patle, Vanita Kshirsagar

Department of Artificial Intelligence and Data Science, Dr. D. Y. Patil Institute of Technology, Pune, Maharashtra 411018, India

Image Denoising Self-Supervised Image Denoising U-Net Denoising Autoencoders

Open paper AskPDF arXiv

Deep learning for medical image restoration is often constrained by the need for paired training data. Acquiring perfectly registered clean-noisy radiographs in vivo is impractical due to patient motion and radiation-dose limits. To address this, we employ a self-supervised Noise2Noise paradigm that trains on independently corrupted observations without paired clean images. We propose Denoise X, a lightweight self-supervised U-Net model (7.79M parameters) for suppressing quantum mottle and electronic readout noise in low-dose chest radiographs. It is trained on the NIH ChestX-ray14 dataset (112,120 images) using a stochastic Poisson-Gaussian noise simulator. Zero-shot evaluation on the unseen Montgomery County dataset achieved a PSNR of 36.09 dB and SSIM of 0.8806, outperforming the Bilateral filter while preserving high-frequency anatomical details. Using patch-wise inference, Denoise X processes native-resolution chest radiographs in ~2.2 s per image on a Tesla P100 GPU. Cross-domain evaluation on the Shenzhen dataset achieved 36.44 dB PSNR and 0.9099 SSIM, showing strong generalization. For resource-constrained deployment, the model was converted into a 31.16 MB ONNX model for efficient CPU inference on non-DICOM images.