Metraipolis › archive › dc_b2dc0a4e6add
Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion — arXiv:2610.07206
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07206
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:25.507Z
- SHA-256 of the archived text
e18f25be1592f7d07dc1b24aac87ea2dd30dcce8c60f736f7b985dcc27c07f18- Stable URL of this page
https://metraipolis.com/documento/dc_b2dc0a4e6add
How to cite
Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion — arXiv:2610.07206 — arXiv (en), https://arxiv.org/abs/2610.07206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2dc0a4e6add (Metraipolis archive dc_b2dc0a4e6add, sha256 e18f25be1592f7d07dc1b24aac87ea2dd30dcce8c60f736f7b985dcc27c07f18)
BibTeX
@misc{dcb2dc0a4e6add,
title = {Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion — arXiv:2610.07206},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07206},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2dc0a4e6add; sha256 e18f25be1592f7d07dc1b24aac87ea2dd30dcce8c60f736f7b985dcc27c07f18},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper introduces an energy-adaptive noise scheduling and whitening strategy for transform-domain diffusion models. Existing spectral diffusion methods account for the non-uniform statistics of transform coefficients through coefficient scaling, normalization, or frequency prioritization, while the forward diffusion noise schedule remains largely independent of the underlying spectral-energy distribution. We investigate whether the temporal evolution of the forward diffusion process should also follow the spectral organization of natural images. The proposed formulation combines global spectral whitening with energy-conditioned noise allocation that jointly modulates the injected noise according to the energy of individual transform coefficients and an image-dependent energy path over diffusion time. The resulting forward process preserves Gaussian transitions with closed-form marginals and remains compatible with standard DDPM and DDIM procedures without modifying the diffusion architecture. Experiments on CIFAR-10 demonstrate the contribution of the proposed energy-conditioned noise schedule and spectral whitening, reducing Fréchet Inception Distance from 142.48 for a compact DCTdiff U-Net variant to 100.45. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2610.07206 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.483Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).