mlsanityData to 14 Oct 2026

Poisson Flow Consistency Training

arXiv 2510.21857 ↗First posted 23 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The Poisson Flow Consistency Model (PFCM) is a consistency-style model based on the robust Poisson Flow Generative Model++ (PFGM++) which has achieved success in unconditional image generation and CT image denoising. Yet the PFCM can only be trained in distillation which limits the potential of the PFCM in many data modalities. The objective of this research was to create a method to train the PFCM in isolation called Poisson Flow Consistency Training (PFCT). The perturbation kernel was leveraged to remove the pretrained PFGM++, and the sinusoidal discretization schedule and Beta noise distribution were introduced in order to facilitate adaptability and improve sample quality. The model was applied to the task of low dose computed tomography image denoising and improved the low dose image in terms of LPIPS and SSIM. It also displayed similar denoising effectiveness as models like the Consistency Model. PFCT is established as a valid method of training the PFCM from its effectiveness in denoising CT images, showing potential with competitive results to other generative models. Further study is needed in the precise optimization of PFCT and in its applicability to other generative modeling tasks. The framework of PFCT creates more flexibility for the ways in which a PFCM can be created and can be applied to the field of generative modeling.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 29 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

19 of 29 references.

References · 19

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  6. 2023Consistency Modelscited by 1,822
  7. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  8. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  9. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  10. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  11. 2023Improved Techniques for Training Consistency Modelscited by 439
  12. 2022Poisson Flow Generative Modelscited by 95
7 more
  1. 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
  2. 2021DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoisingcited by 46
  3. 2019Quadratic Autoencoder (Q-AE) for Low-dose CT Denoisingcited by 35
  4. 2022Full-band General Audio Synthesis with Score-based Diffusioncited by 32
  5. 2024PFCM: Poisson flow consistency models for low-dose CT image denoisingcited by 5
  6. 2024High Noise Scheduling is a Mustcited by 1
  7. 2024Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniquescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023PPFM: Image denoising in photon-counting CT using single-step posterior sampling Poisson flow generative models
  2. 2025Poisson Flow Joint Model for Multiphase contrast-enhanced CT ↗
  3. 2024Truncated Consistency Models
  4. 2025VCT: Training Consistency Models with Variational Noise Coupling
  5. 2024Stable Consistency Tuning: Understanding and Improving Consistency Models
  6. 2024Improving Consistency Models with Generator-Augmented Flows
  7. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
  8. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistency