English

Rectified Noise: A Generative Model Using Positive-incentive Noise

Machine Learning 2025-11-13 v2

Abstract

Rectified Flow (RF) has been widely used as an effective generative model. Although RF is primarily based on probability flow Ordinary Differential Equations (ODE), recent studies have shown that injecting noise through reverse-time Stochastic Differential Equations (SDE) for sampling can achieve superior generative performance. Inspired by Positive-incentive Noise (pi-noise), we propose an innovative generative algorithm to train pi-noise generators, namely Rectified Noise (RN), which improves the generative performance by injecting pi-noise into the velocity field of pre-trained RF models. After introducing the Rectified Noise pipeline, pre-trained RF models can be efficiently transformed into pi-noise generators. We validate Rectified Noise by conducting extensive experiments across various model architectures on different datasets. Notably, we find that: (1) RF models using Rectified Noise reduce FID from 10.16 to 9.05 on ImageNet-1k. (2) The models of pi-noise generators achieve improved performance with only 0.39% additional training parameters.

Keywords

Cite

@article{arxiv.2511.07911,
  title  = {Rectified Noise: A Generative Model Using Positive-incentive Noise},
  author = {Zhenyu Gu and Yanchen Xu and Sida Huang and Yubin Guo and Hongyuan Zhang},
  journal= {arXiv preprint arXiv:2511.07911},
  year   = {2025}
}

Comments

Accepted by AAAI 2026

R2 v1 2026-07-01T07:31:23.836Z