Poisson Flow Consistency Training

TL;DR

This paper introduces Poisson Flow Consistency Training (PFCT), a new method enabling the training of Poisson Flow Consistency Models (PFCMs) independently, enhancing flexibility and applicability in generative modeling tasks like CT image denoising.

Contribution

The paper proposes PFCT, a novel training approach for PFCMs that removes the need for distillation from PFGM++, expanding their use across various data modalities.

Findings

PFCT achieves competitive denoising results in low dose CT images.

The method improves sample quality through sinusoidal discretization and Beta noise.

PFCT demonstrates potential for broader application in generative modeling.

Abstract

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.