Metraipolis › archive › dc_aae4e34bac82

When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative Enhancement — arXiv:2610.21335

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21335
License (as archived)
CC0-1.0
Archived
2026-10-16T10:25:12.005Z
SHA-256 of the archived text
9a2ded2618c7c57dd238c2dfecdce4227f4860c9bcb4b06f60b251375692b877
Stable URL of this page
https://metraipolis.com/documento/dc_aae4e34bac82

How to cite

When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative Enhancement — arXiv:2610.21335 — arXiv (en), https://arxiv.org/abs/2610.21335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aae4e34bac82 (Metraipolis archive dc_aae4e34bac82, sha256 9a2ded2618c7c57dd238c2dfecdce4227f4860c9bcb4b06f60b251375692b877)
BibTeX
@misc{dcaae4e34bac82,
  title = {When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative Enhancement — arXiv:2610.21335},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21335},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aae4e34bac82; sha256 9a2ded2618c7c57dd238c2dfecdce4227f4860c9bcb4b06f60b251375692b877},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative low-light enhancers recover plausible texture but may hallucinate structure; restoration networks preserve structure but can leave regions under-enhanced, and neither advantage is spatially uniform. Therefore, we formulate selective generative enhancement as a decision problem: determine where overriding a frozen base expert is beneficial and refuse to switch when the evidence is insufficient. We propose VetoNet, an auditable regional routing framework centered on a certified veto. It first measures the complementary strengths and routing direction of a frozen restoration generative pair, then predicts the utility of regional overrides from deployment-available signals alone and admits an override only when a distribution-free harm-budget certificate says the perceptual (LPIPS) risk budget allows it. Experiments across multiple expert pairs and domains show that VetoNet adapts its routing behavior to the strength and reliability of the available evidence. When expert complementarity is sufficiently predictable, it achieves statistically significant certified gains; when the relative strengths of the experts change, it correspondingly reverses the routing direction; and when routing evidence is weak or affected by cross-domain shift, it conservatively vetoes switching.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.21335 — 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 2026-10-16T08:48:02.893Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).