mlsanityData to 7 Oct 2026

SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder

arXiv 2403.17502 ↗First posted 26 Mar 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The data bottleneck has emerged as a fundamental challenge in learning based image restoration methods. Researchers have attempted to generate synthesized training data using paired or unpaired samples to address this challenge. This study proposes SeNM-VAE, a semi-supervised noise modeling method that leverages both paired and unpaired datasets to generate realistic degraded data. Our approach is based on modeling the conditional distribution of degraded and clean images with a specially designed graphical model. Under the variational inference framework, we develop an objective function for handling both paired and unpaired data. We employ our method to generate paired training samples for real-world image denoising and super-resolution tasks. Our approach excels in the quality of synthetic degraded images compared to other unpaired and paired noise modeling methods. Furthermore, our approach demonstrates remarkable performance in downstream image restoration tasks, even with limited paired data. With more paired data, our method achieves the best performance on the SIDD dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 71 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

43 of 71 references.

References · 43

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  3. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2022Denoising Diffusion Restoration Modelscited by 951
  6. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  7. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  8. 2022Simple Baselines for Image Restorationcited by 701
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  10. 2015Generating Sentences from a Continuous Spacecited by 607
  11. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  12. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
31 more
  1. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  2. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  3. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  4. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  5. 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
  6. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  7. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  8. 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
  9. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  10. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 177
  11. 2019Variational Denoising Network: Toward Blind Noise Modeling and Removalcited by 117
  12. 2019Frequency Separation for Real-World Super-Resolutioncited by 115
  13. 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
  14. 2020Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generationcited by 101
  15. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94
  16. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 92
  17. 2020Unsupervised Real-world Image Super Resolution via Domain-distance Aware Trainingcited by 83
  18. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  19. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  20. 2022C2N: Practical Generative Noise Modeling for Real-World Denoisingcited by 56
  21. 2019Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancementscited by 54
  22. 2022Dancing under the stars: video denoising in starlightcited by 47
  23. 2022CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Imagecited by 45
  24. 2019AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 34
  25. 2023Random Sub-Samples Generation for Self-Supervised Real Image Denoisingcited by 31
  26. 2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
  27. 2023Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branchescited by 29
  28. 2022Modeling sRGB Camera Noise with Normalizing Flowscited by 28
  29. 2019Natural Image Noise Datasetcited by 20
  30. 2022Learn from Unpaired Data for Image Restoration: A Variational Bayes Approachcited by 18
  31. 2023Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoisingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025MoCLIP: Motion-Aware Fine-Tuning and Distillation of CLIP for Human Motion Generationcited by 2
  2. 2025Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniquescited by 1
  3. 2026Unpaired Joint Distribution Modeling via Multi-Scale Image Representationscited by 0
  4. 2026YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generationcited by 0