mlsanityData to 7 Oct 2026

AmbientFlow: Invertible generative models from incomplete, noisy measurements

arXiv 2309.04856 ↗First posted 9 Sep 2023cs.LG cs.AI eess.IVcited by 11

Not on the map. Why?

Abstract (arXiv)

Generative models have gained popularity for their potential applications in imaging science, such as image reconstruction, posterior sampling and data sharing. Flow-based generative models are particularly attractive due to their ability to tractably provide exact density estimates along with fast, inexpensive and diverse samples. Training such models, however, requires a large, high quality dataset of objects. In applications such as computed imaging, it is often difficult to acquire such data due to requirements such as long acquisition time or high radiation dose, while acquiring noisy or partially observed measurements of these objects is more feasible. In this work, we propose AmbientFlow, a framework for learning flow-based generative models directly from noisy and incomplete data. Using variational Bayesian methods, a novel framework for establishing flow-based generative models from noisy, incomplete data is proposed. Extensive numerical studies demonstrate the effectiveness of AmbientFlow in learning the object distribution. The utility of AmbientFlow in a downstream inference task of image reconstruction is demonstrated.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 28 of its 51 references that are in the map. First posted on arXiv 9 Sep 2023.

Builds on

28 of 51 references.

References · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2019An Introduction to Variational Autoencoderscited by 997
  9. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  10. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  11. 2015Importance Weighted Autoencoderscited by 454
  12. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
16 more
  1. 2017Compressed Sensing using Generative Modelscited by 337
  2. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  3. 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 93
  4. 2020On hallucinations in tomographic image reconstructioncited by 66
  5. 2020Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imagingcited by 57
  6. 2021Instance-Optimal Compressed Sensing via Posterior Samplingcited by 43
  7. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
  8. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31
  9. 2021Conditional Invertible Neural Networks for Diverse Image-to-Image Translationcited by 24
  10. 2020Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstructioncited by 19
  11. 2021Prior Image-Constrained Reconstruction using Style-Based Generative Modelscited by 19
  12. 2022Conditional Injective Flows for Bayesian Imagingcited by 13
  13. 2021Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networkscited by 12
  14. 2022Assessing the ability of generative adversarial networks to learn canonical medical image statisticscited by 11
  15. 2023Ideal Observer Computation by Use of Markov-Chain Monte Carlo with Generative Adversarial Networkscited by 6
  16. 2020Principled Interpolation in Normalizing Flowscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 3.

11 papers.

  1. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Datacited by 32
  2. 2024How much is a noisy image worth? Data Scaling Laws for Ambient Diffusioncited by 18
  3. 2025Ambient Diffusion Omni: Training Good Models with Bad Datacited by 18
  4. 2024Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Imagescited by 12
  5. 2025Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generationcited by 7
  6. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurementscited by 3
  7. 2026Ambient Dataloops: Generative Models for Dataset Refinementcited by 2
  8. 2024Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencodercited by 1
  9. 2025Double Blind Imaging with Generative Modelingcited by 1
  10. 2026Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Datacited by 1
  11. 2026Noise-Robust Conditional Flow Matching: Generating Clean Samples from Noisy Datasetscited by 0