Spectral Forcing

Introduction

Spectral Forcing (SF) is based on the observation that under rectified-flow diffusion and natural-image power-law spectra, a moving frequency front separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each timestep. SF imposes this boundary directly via a 2D-DCT mask whose cutoff expands with the diffusion time and becomes the identity at the data endpoint, showing the network the signal and hiding the noise.

BibTex

@misc{fan2026show,
  title         = {{Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion}},
  author        = {Fan, Weichen and Diao, Haiwen and Wu, Penghao and Liu, Ziwei},
  year          = {2026},
  eprint        = {2606.15236},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  doi           = {10.48550/arXiv.2606.15236},
  url           = {https://arxiv.org/abs/2606.15236}
}

--- license: apache-2.0 pipeline_tag: unconditional-image-generation --- # Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion This repository contains the weights for **Spectral Forcing**, a parameter-free, time-conditional low-pass operator that makes the coarse-to-fine structure of diffusion explicit at the input of a pixel-space model. - **Paper:** [Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion](https://arxiv.org/abs/2606.15236) - **Github Repository:** [https://github.com/WeichenFan/Spectral_Forcing](https://github.com/WeichenFan/Spectral_Forcing) ## Introduction Spectral Forcing (SF) is based on the observation that under rectified-flow diffusion and natural-image power-law spectra, a moving frequency front separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each timestep. SF imposes this boundary directly via a 2D-DCT mask whose cutoff expands with the diffusion time and becomes the identity at the data endpoint, showing the network the signal and hiding the noise. ## BibTex ```bibtex @misc{fan2026show, title = {{Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion}}, author = {Fan, Weichen and Diao, Haiwen and Wu, Penghao and Liu, Ziwei}, year = {2026}, eprint = {2606.15236}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, doi = {10.48550/arXiv.2606.15236}, url = {https://arxiv.org/abs/2606.15236} } ```