Metraipolis › archive › dc_7e26d0c8098e
Direct Conditional Transition Sampling for Diffusion Inverse Problems — arXiv:2609.14596
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14596
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:33:52.649Z
- SHA-256 of the archived text
936eb0be487e97e5f1a891c3bd95b61a43916b58b64a0d5db27ee2c4f6c4f042- Stable URL of this page
https://metraipolis.com/documento/dc_7e26d0c8098e
How to cite
Direct Conditional Transition Sampling for Diffusion Inverse Problems — arXiv:2609.14596 — arXiv (en), https://arxiv.org/abs/2609.14596 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7e26d0c8098e (Metraipolis archive dc_7e26d0c8098e, sha256 936eb0be487e97e5f1a891c3bd95b61a43916b58b64a0d5db27ee2c4f6c4f042)
BibTeX
@misc{dc7e26d0c8098e,
title = {Direct Conditional Transition Sampling for Diffusion Inverse Problems — arXiv:2609.14596},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14596},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7e26d0c8098e; sha256 936eb0be487e97e5f1a891c3bd95b61a43916b58b64a0d5db27ee2c4f6c4f042},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14596. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent posterior refresh can improve global correction by sampling a clean conditional and re-noising it, but its practical realization requires probability-flow ODE integration and clean-space Markov chain Monte Carlo (MCMC). We propose Direct Conditional Transition Sampling (DCTS), a direct stochastic-flow approximation to the same ideal refresh target. Rather than explicitly drawing a clean sample, DCTS estimates the measurement-conditioned clean mean along a short inner path and transports Gaussian source noise directly to the next noisy state. A denoiser-compatible sufficient statistic and a covariance-scaled operator update enable this conditional-mean estimation. Experiments on four inverse problems demonstrate that DCTS achieves competitive reconstruction quality with up to $16.8\times$ speedups over competing methods. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in stat.ML). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.14596 — 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 2026-10-16T00:15:49.207Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).