Metraipolis › archive › dc_e648e32dcf8e
Diffusion Based Unpaired Data Learning for Inverse Problems — arXiv:2609.01370
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01370
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:54.460Z
- SHA-256 of the archived text
5dacd8b1427dce1a5d364b80f602a4eb06842405d78db0b362c54e9af7d5d0fa- Stable URL of this page
https://metraipolis.com/documento/dc_e648e32dcf8e
How to cite
Diffusion Based Unpaired Data Learning for Inverse Problems — arXiv:2609.01370 — arXiv (en), https://arxiv.org/abs/2609.01370 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e648e32dcf8e (Metraipolis archive dc_e648e32dcf8e, sha256 5dacd8b1427dce1a5d364b80f602a4eb06842405d78db0b362c54e9af7d5d0fa)
BibTeX
@misc{dce648e32dcf8e,
title = {Diffusion Based Unpaired Data Learning for Inverse Problems — arXiv:2609.01370},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01370},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e648e32dcf8e; sha256 5dacd8b1427dce1a5d364b80f602a4eb06842405d78db0b362c54e9af7d5d0fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01370. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data is important in many deep learning-based inverse problem solvers. However, obtaining sufficient paired data in many scenarios remains highly challenging, while unpaired data is cheap. To maximize data utilization, this paper proposes LUD-DIF, a diffusion-based approach for solving inverse problems with unpaired data. Starting from the evidence lower bound (ELBO) of the joint distribution, we decouple it into two independent diffusion processes under the weak-coupling assumption. The method provides theoretical support from a variational inference perspective, derives the loss function, quantitatively analyzes the error bound introduced by the assumption, and offers a theorem-motivated heuristic for hyperparameter selection. Experimental results demonstrate that LUD-DIF achieves outstanding performance on multiple image inverse problems, validating its effectiveness and generalization capability in unpaired inverse problem settings. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01370 — 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 2026-10-17T07:00:58.983Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).